© 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
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-262K
    4. 241482
    Prev
    Next
    INDEX
    Explanations

    magic

    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
    صميم
    0.61
    udur
    0.56
     اللون
    0.56
    copyOf
    0.56
    рез
    0.54
    न्हा
    0.54
     electrophoresis
    0.54
    동
    0.54
    <?=$
    0.52
    Архівовано
    0.52
    POSITIVE LOGITS
     magical
    0.70
     magic
    0.65
     заканчи
    0.63
    ੈਂ
    0.62
     Magic
    0.61
     rhymes
    0.59
     Поль
    0.59
     juicy
    0.56
     rhyme
    0.56
     Magical
    0.56
    Activations Density 0.000%

    No Known Activations