© 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. 1152
    Prev
    Next
    INDEX
    Explanations

    relevant

    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
    "}
    -2.33
    </i>
    -2.27
     escuchadas
    -2.03
    
    -2.02
    *}[
    -1.88
    𖣔
    -1.88
    ка
    -1.86
    ";
    -1.82
    skjaer
    -1.80
    andowski
    -1.79
    POSITIVE LOGITS
    which
    2.31
     coincident
    2.17
    relevant
    1.89
    Ꮀ
    1.88
    </em>
    1.88
    n
    1.80
    H
    1.78
     الفلسط
    1.77
    T
    1.77
     blumen
    1.76
    Activations Density 0.028%

    No Known Activations