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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 44832
    Prev
    Next
    INDEX
    Explanations

    good manufacturing, strong evidence, marketing slogan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sélectionner
    0.92
     mètres
    0.91
    tä
    0.83
     població
    0.82
    訒
    0.82
    edict
    0.82
    黢
    0.82
     vaš
    0.81
     gacchati
    0.81
    tram
    0.80
    POSITIVE LOGITS
    ory
    0.81
    ihin
    0.79
    й
    0.78
     Enzym
    0.75
     التح
    0.75
    э
    0.75
     ch
    0.73
     Section
    0.73
     Fund
    0.73
    力
    0.73
    Activations Density 0.000%

    No Known Activations