© 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. 112867
    Prev
    Next
    INDEX
    Explanations

    Norwich and Anglia

    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
    
    -2.69
     crux
    -2.69
    il
    -2.67
     unequivocal
    -2.45
     scandalous
    -2.44
     sneaky
    -2.42
    on
    -2.41
    ⸂
    -2.39
     größer
    -2.39
     каждой
    -2.38
    POSITIVE LOGITS
    s
    3.80
    which
    3.00
    "));
    2.48
    獁
    2.42
    '
    2.42
     και
    2.39
    },
    2.36
    ."
    2.30
    ación
    2.28
    where
    2.17
    Activations Density 0.021%

    No Known Activations