© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 54000
    Prev
    Next
    INDEX
    Explanations

    delayed wound

    np_acts-logits-general · gemini-2.5-flash-lite

    code-related structural elements like brackets, function definitions, and class declarations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ربی
    -0.85
    錠
    -0.84
     by
    -0.83
    جام
    -0.79
    溝通
    -0.79
    cribing
    -0.78
    딩
    -0.77
    Medicine
    -0.77
     now
    -0.77
    漣
    -0.77
    POSITIVE LOGITS
    ;}
    0.93
     podría
    0.90
     leſs
    0.87
    ὸ
    0.84
     إلى
    0.82
     mirador
    0.82
    ネギ
    0.80
    久しぶり
    0.79
     desp
    0.77
     void
    0.77
    Activations Density 0.006%

    No Known Activations