© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11336
    Prev
    Next
    INDEX
    Explanations

    same data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ablon
    -0.74
    IsSuccess
    -0.73
    jspb
    -0.73
    reci
    -0.71
    下一个
    -0.71
    ITURE
    -0.70
     biztons
    -0.68
    읖
    -0.68
    ッタリ
    -0.66
    guna
    -0.66
    POSITIVE LOGITS
     same
    3.08
    same
    2.39
    Same
    2.36
     again
    2.31
     Same
    2.13
     identical
    2.08
    SAME
    1.91
    again
    1.86
     aynı
    1.85
     aforementioned
    1.83
    Activations Density 0.035%

    No Known Activations