© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13880
    Prev
    Next
    INDEX
    Explanations

    common sense and common data sources

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is specialized to detect the token “Common” (as in phrases like “Common Core,” “Common Ground,” etc.).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    the phrase "Common" followed by a capitalizable noun (especially in organizational names like "Common Core", "Common Ground", "Common Purpose").

    oai_token-act-pair · claude-4-5-sonnet
    Triggered by @jyhe0408

    mentions of “common” and its morphological or compound uses, especially when capitalized in proper names, titles, or set phrases.

    oai_token-act-pair · gpt-5
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    漳
    0.70
    アリング
    0.67
     แชร์
    0.66
     इंस्टीट्यूट
    0.64
     заповед
    0.63
    的作品
    0.61
     sharp
    0.60
    satz
    0.60
     Supreme
    0.60
    ளிலும்
    0.60
    POSITIVE LOGITS
     denominator
    1.05
    Common
    1.05
     Common
    1.03
    alities
    0.99
     denominators
    0.98
    denominator
    0.96
     common
    0.95
    ality
    0.94
    common
    0.91
     COMMON
    0.91
    Activations Density 0.079%

    No Known Activations