© 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. 72340
    Prev
    Next
    INDEX
    Explanations

    licenses, solution, vevent, cwe

    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
     it
    -1.18
    calips
    -1.11
    子は
    -1.10
     anyone
    -1.07
    知道了
    -1.00
     Brunnen
    -0.99
     Ums
    -0.99
    ezy
    -0.99
     everyone
    -0.98
     sigui
    -0.97
    POSITIVE LOGITS
     считает
    1.03
     and
    1.02
     phénomène
    1.02
    secuencias
    1.00
    lesssim
    0.99
    arynge
    0.99
     protože
    0.99
     bytu
    0.98
    ্ন
    0.98
     effectual
    0.96
    Activations Density 0.001%

    No Known Activations