Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 41-GEMMASCOPE-2-RES-65K
    4. 1003
    Prev
    Next
    INDEX
    Explanations

    informal language

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_width_65k_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
    […]
    0.69
    [...]
    0.67
    <unused2165>
    0.63
     [...
    0.62
    ...",
    0.60
    (...
    0.60
     [...]
    0.60
    ...");
    0.57
    <unused2126>
    0.57
    ・・・
    0.56
    POSITIVE LOGITS
     ihe
    0.79
     lhe
    0.75
     ail
    0.72
     tn
    0.71
     thc
    0.68
     tho
    0.66
     ln
    0.65
     tha
    0.64
     wl
    0.63
     ies
    0.63
    Activations Density 0.053%

    No Known Activations