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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 112557
    Prev
    Next
    INDEX
    Explanations

    Python code snippets

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

    indentation or whitespace at the beginning of lines in code, particularly in Python code blocks.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    镲
    -2.33
    嗵
    -2.17
    '));
    -2.16
    樯
    -2.08
    something
    -2.08
     parachoque
    -2.02
    
    -1.98
    釹
    -1.96
     rése
    -1.95
    sich
    -1.94
    POSITIVE LOGITS
     if
    2.33
    </h2>
    2.17
     also
    2.13
     actually
    2.09
     first
    2.06
     same
    2.00
     resulting
    1.88
     
    1.80
     by
    1.79
     larger
    1.73
    Activations Density 0.012%

    No Known Activations