© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 256
    Prev
    Next
    INDEX
    Explanations

    Can you

    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_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
     there
    -2.80
     to
    -2.33
     as
    -2.19
     if
    -2.19
     for
    -2.13
     I
    -2.03
    );
    -1.86
    There
    -1.77
    };
    -1.76
    for
    -1.72
    POSITIVE LOGITS
    囖
    1.95
    TryDecode
    1.92
    芣
    1.89
    Stap
    1.88
    caneca
    1.81
     .........
    1.77
    
    1.77
     .......
    1.75
    够了
    1.73
    苤
    1.73
    Activations Density 0.006%

    No Known Activations