© 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. 20982
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    ↵↵
    -2.09
    -
    -1.88
     لئے
    -1.73
    不可思议
    -1.70
    十分的
    -1.61
    当即
    -1.55
    下意识
    -1.55
    
    -1.55
    alors
    -1.49
    élaboration
    -1.48
    POSITIVE LOGITS
    ONSORED
    1.50
    ！"
    1.49
    www
    1.45
    щении
    1.42
     //
    1.41
     on
    1.41
    되어
    1.41
    You
    1.39
     /
    1.39
    //
    1.39
    Activations Density 0.005%

    No Known Activations