© 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. 15005
    Prev
    Next
    INDEX
    Explanations

    code and symbols

    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
    %
    0.71
    altz
    0.57
    0.56
     just
    0.55
     %
    0.55
    %%
    0.55
    amily
    0.54
    %%%%%%%%%%%%%
    0.54
    ĺ
    0.53
    Javascript
    0.52
    POSITIVE LOGITS
     defList
    0.56
    䄪
    0.55
    metaTag
    0.55
    marginX
    0.55
    象棋
    0.54
    roff
    0.54
    煙
    0.53
    城镇
    0.53
    㕧
    0.52
     resa
    0.52
    Activations Density 0.000%

    No Known Activations