© 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
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-262K
    7. 241541
    Prev
    Next
    INDEX
    Explanations

    technical/logic terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_262k_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
    CONCLUS
    0.77
    LookAndFeel
    0.65
    }^{+}\
    0.64
     etiqueta
    0.63
     شخصی
    0.60
     فور
    0.60
    ICAS
    0.59
    dfe
    0.59
    +}^{
    0.59
    SIX
    0.59
    POSITIVE LOGITS
    吴
    0.61
    ま
    0.58
     цю
    0.57
    保存
    0.56
     والر
    0.55
     lowering
    0.54
     pursuing
    0.53
    吳
    0.52
     relationships
    0.52
    明る
    0.52
    Activations Density 0.000%

    No Known Activations