© 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. 2259
    Prev
    Next
    INDEX
    Explanations

    python imports

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

    This neuron fires strongly on multi-word product, software, or brand names.

    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
     इनवर्स
    0.61
    serverId
    0.61
    сле
    0.61
    encher
    0.58
     切
    0.58
    贲
    0.57
    डिएट
    0.56
     LSTM
    0.56
     mulberry
    0.56
    ኢ
    0.56
    POSITIVE LOGITS
    ⓘ
    0.86
    Descripción
    0.81
    Detal
    0.68
    Beschreibung
    0.68
    Details
    0.67
    ABOUT
    0.66
    About
    0.65
    Presentation
    0.63
     バッグ
    0.62
    Descrição
    0.61
    Activations Density 0.057%

    No Known Activations