© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2024
    Prev
    Next
    INDEX
    Explanations

    mathematical constants and sequences

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

    This neuron identifies content words (especially titles, key nouns, and numeric details) within bibliographic reference entries.

    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
     in
    0.77
     is
    0.70
     for
    0.70
     to
    0.69
    ↵
    0.66
     on
    0.66
     at
    0.66
     de
    0.65
     a
    0.64
     was
    0.62
    POSITIVE LOGITS
    第壹百
    0.71
     Fleurit
    0.67
    Соцмережа
    0.63
     遊ん
    0.63
    शिलाजीत
    0.63
    崞
    0.63
    getFocusAreas
    0.61
    ፕሮ
    0.61
     halfCanvas
    0.61
     inactivació
    0.61
    Activations Density 0.028%

    No Known Activations