© 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-65K
    7. 15157
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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_65k_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
     breed
    0.60
     சிவா
    0.59
     mudança
    0.59
     পিটার
    0.59
     mudanças
    0.57
    dometer
    0.57
     depositors
    0.56
    摶
    0.55
     измене
    0.55
     изменить
    0.55
    POSITIVE LOGITS
    凹
    0.69
    _{\
    0.60
    ინისტრ
    0.57
    扁
    0.55
    閣
    0.55
     Friction
    0.53
     Crack
    0.52
    nash
    0.52
    _{+}
    0.51
    Ω
    0.50
    Activations Density 0.000%

    No Known Activations