© 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. 22-GEMMASCOPE-RES-131K
    7. 33488
    Prev
    Next
    INDEX
    Explanations

    code return statements

    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_22/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
     جراحی
    -0.94
     Sosial
    -0.92
     formulaire
    -0.91
    راحة
    -0.88
     anún
    -0.88
    Ᏹ
    -0.87
     ਲਈ
    -0.85
    ')){
    -0.85
    țion
    -0.84
    hört
    -0.82
    POSITIVE LOGITS
    return
    2.78
     return
    1.45
     would
    1.36
     but
    1.25
     than
    1.11
     returning
    0.95
    However
    0.95
    usão
    0.94
     then
    0.91
     mejorando
    0.91
    Activations Density 0.004%

    No Known Activations