© 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. 2562
    Prev
    Next
    INDEX
    Explanations

    describing colors

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

    This neuron fires on Bible‐style verse references and related numeric citation 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
     ด่า
    0.49
     इस्तीफा
    0.48
     Enseñanza
    0.47
    ယောက်
    0.45
    妬
    0.45
     offended
    0.44
    Isra
    0.44
    iritual
    0.44
    潰
    0.44
    ewnętr
    0.43
    POSITIVE LOGITS
     voici
    0.49
     Thou
    0.49
     Behold
    0.49
    🎵
    0.49
     Oh
    0.45
     yada
    0.45
     thou
    0.44
    ♫
    0.44
    Let
    0.43
     let
    0.43
    Activations Density 0.196%

    No Known Activations