© 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. 84700
    Prev
    Next
    INDEX
    Explanations

    paste this

    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
    
    -1.73
    
    -1.67
     Sebagai
    -1.63
     Sakit
    -1.59
     его
    -1.59
     هذا
    -1.55
     milliards
    -1.54
     jego
    -1.53
     gik
    -1.53
     वाप
    -1.52
    POSITIVE LOGITS
     in
    2.09
     the
    1.76
    ;
    1.73
     into
    1.65
     their
    1.55
     most
    1.48
    </b>
    1.42
    g
    1.38
    了很多
    1.38
    迥
    1.37
    Activations Density 0.041%

    No Known Activations