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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10214
    Prev
    Next
    INDEX
    Explanations

    must be

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

    The neuron fires on the possessive suffix "'s," marking genitive constructions (e.g. women’s, show’s).

    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
     సం
    0.59
     அவர்களின்
    0.58
    监
    0.58
     指
    0.57
     NUMBER
    0.53
    hamton
    0.52
    数
    0.52
     Christophe
    0.52
     बता
    0.52
     एक्टिव
    0.51
    POSITIVE LOGITS
    쌓
    0.53
    >=
    0.52
    плы
    0.51
    を書
    0.51
     ≥
    0.50
    ≥
    0.49
    邪
    0.49
     pregn
    0.48
    ូ
    0.48
     Bek
    0.47
    Activations Density 0.048%

    No Known Activations