© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 94461
    Prev
    Next
    INDEX
    Explanations

    company that

    np_acts-logits-general · gemini-2.5-flash-lite

    historical analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     vielfält
    0.55
     resistentes
    0.52
     прибыли
    0.52
     integrantes
    0.51
     fă
    0.50
     သိ
    0.50
    netHex
    0.50
    <unused564>
    0.50
    <unused662>
    0.49
     deportes
    0.49
    POSITIVE LOGITS
    k
    0.61
    o
    0.57
    W
    0.55
    Help
    0.54
    JECTION
    0.53
    K
    0.52
    Non
    0.52
    Delete
    0.50
    Warning
    0.49
    SO
    0.48
    Activations Density 0.000%

    No Known Activations