© 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. 241401
    Prev
    Next
    INDEX
    Explanations

    are

    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
    dade
    0.57
    çu
    0.57
     luscious
    0.56
     Californian
    0.56
    ాము
    0.55
    吆
    0.55
    dale
    0.55
     aéri
    0.54
     Wür
    0.54
     युवाओ
    0.54
    POSITIVE LOGITS
     индек
    0.68
     शनि
    0.65
    indexing
    0.65
    グラフ
    0.64
    Indexing
    0.64
    綎
    0.63
    indexes
    0.62
    拠点
    0.61
    لب
    0.60
    Encryption
    0.60
    Activations Density 0.000%

    No Known Activations