© 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. 15424
    Prev
    Next
    INDEX
    Explanations

    Core

    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
     
    -3.06
     Then
    -2.52
    ㈬
    -2.42
     knap
    -2.34
    
    -2.33
     you
    -2.31
     juga
    -2.23
     drit
    -2.22
    時も
    -2.20
    也会
    -2.17
    POSITIVE LOGITS
     Schiffe
    2.34
    霰
    2.33
     arcane
    2.33
    ు
    2.31
     市场
    2.28
    ে
    2.25
    o
    2.22
     Bäume
    2.19
     师
    2.19
     exacting
    2.14
    Activations Density 0.010%

    No Known Activations