© 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. 241512
    Prev
    Next
    INDEX
    Explanations

    technical instructions

    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
     Lynda
    0.54
     createCanvas
    0.53
    ociazione
    0.52
     elliptic
    0.51
     IllegalArgument
    0.51
    prj
    0.51
     은
    0.50
    itev
    0.50
     Cem
    0.50
     İşte
    0.49
    POSITIVE LOGITS
     играть
    0.61
     akár
    0.56
     godfather
    0.55
    ঠাকুর
    0.55
    を加
    0.55
    梢
    0.55
    mainan
    0.55
    improvement
    0.54
    generally
    0.54
    والي
    0.54
    Activations Density 0.000%

    No Known Activations