© 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. 10-GEMMASCOPE-RES-131K
    7. 1091
    Prev
    Next
    INDEX
    Explanations

    Marco

    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
    }
    -2.91
     wußte
    -2.50
     überprü
    -2.50
     glaubte
    -2.34
    ים
    -2.33
    也很
    -2.33
     mogą
    -2.28
    也好
    -2.27
    नलोड
    -2.25
     erklä
    -2.23
    POSITIVE LOGITS
    鶲
    2.86
    am
    2.83
    );
    2.83
    ”،
    2.69
    儈
    2.66
    瀲
    2.45
    らん
    2.44
     lesquels
    2.41
    
    2.39
    没能
    2.38
    Activations Density 0.002%

    No Known Activations