© 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. 40188
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     desarrollando
    -1.09
     famed
    -1.09
     içeris
    -0.98
     typhoon
    -0.96
     overarching
    -0.96
     appropriated
    -0.96
     gewisser
    -0.95
     voicing
    -0.94
     contratto
    -0.93
     resounding
    -0.93
    POSITIVE LOGITS
     sehr
    1.02
     kunne
    1.01
     Menschen
    1.01
     {;
    0.98
     februari
    0.98
    rrrr
    0.97
     agosto
    0.97
    obut
    0.97
    ňuje
    0.94
    ٦
    0.94
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.