© 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. 241531
    Prev
    Next
    INDEX
    Explanations

    technical configuration

    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
    Myst
    0.62
    Final
    0.56
    Asset
    0.53
     Gef
    0.53
     Estates
    0.52
     القرار
    0.52
     मौत
    0.52
    ཇ
    0.52
    ленность
    0.52
    डेट
    0.51
    POSITIVE LOGITS
    kiy
    0.64
     Rudolf
    0.59
     ais
    0.59
     mnist
    0.59
    usahaan
    0.58
     Erasmus
    0.58
    uis
    0.58
     Malcolm
    0.57
     Bismarck
    0.57
    kop
    0.56
    Activations Density 0.000%

    No Known Activations