© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 8153
    Prev
    Next
    INDEX
    Explanations

    common denominators and multiples

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

    This neuron responds to numeric identifiers and references—chapter/section numbers, page citations, equation or figure labels, and similar technical number markers.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ពេល
    0.59
    inded
    0.58
    კ
    0.57
    Expr
    0.56
    mathsf
    0.54
    canonical
    0.52
    andae
    0.51
    yog
    0.51
    constants
    0.51
    ᅴ
    0.51
    POSITIVE LOGITS
     রাষ্ট্রীয়
    0.66
     carriera
    0.66
     শির
    0.64
     eagle
    0.59
     EAG
    0.59
     trooper
    0.58
     라는
    0.58
     거리
    0.57
     qualcuno
    0.57
     aço
    0.57
    Activations Density 0.002%

    No Known Activations