© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67420
    Prev
    Next
    INDEX
    Explanations

    words following specific terms

    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
    廰
    -2.92
    饪
    -2.56
    艄
    -2.47
     called
    -2.30
    
    -2.27
     censi
    -2.16
     assunto
    -2.11
    鑁
    -2.09
    歘
    -2.09
     entram
    -2.08
    POSITIVE LOGITS
    ↵
    2.36
    There
    2.11
    ’
    2.06
    Many
    1.99
    Nearly
    1.98
    Several
    1.95
    Despite
    1.94
    Almost
    1.91
    Every
    1.87
    Unlike
    1.84
    Activations Density 0.000%

    No Known Activations