© 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. 241377
    Prev
    Next
    INDEX
    Explanations

    body parts and structure

    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
     Paj
    0.58
     goodness
    0.55
     కాల
    0.54
    貼
    0.54
     Tav
    0.54
    agne
    0.53
     Kav
    0.53
    zón
    0.53
    పోయింది
    0.52
    Cola
    0.52
    POSITIVE LOGITS
     ERIC
    0.63
     vun
    0.60
    ASTM
    0.57
    ពួក
    0.57
    remark
    0.56
    internal
    0.55
    粎
    0.55
    claw
    0.54
    lack
    0.54
     Internal
    0.54
    Activations Density 0.001%

    No Known Activations