© 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. 21677
    Prev
    Next
    INDEX
    Explanations

    demo examples

    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
    你
    -2.56
     Also
    -2.34
    轳
    -2.30
     también
    -2.28
     englischen
    -2.23
    });
    -2.23
     regiones
    -2.19
     naciones
    -2.19
    also
    -2.17
     也
    -2.17
    POSITIVE LOGITS
    媜
    2.70
     inconvénients
    2.67
    ed
    2.59
    {
    2.56
    
    2.52
    [
    2.48
    鴟
    2.31
    どうか
    2.30
     attaques
    2.27
    涷
    2.27
    Activations Density 0.006%

    No Known Activations