© 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. 14707
    Prev
    Next
    INDEX
    Explanations

    Excel sheets

    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
    ]^
    -1.72
    
    -1.58
     تصریح
    -1.56
     abou
    -1.51
     litros
    -1.48
    operatively
    -1.47
    胪
    -1.45
    ""}
    -1.44
    泔
    -1.43
    亓
    -1.42
    POSITIVE LOGITS
    (
    1.96
     it
    1.78
     acoged
    1.70
     untuk
    1.65
    有很多
    1.65
     maravillosa
    1.63
    قيق
    1.57
    Table
    1.55
     owing
    1.52
    来源
    1.49
    Activations Density 0.011%

    No Known Activations