© 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. 205225
    Prev
    Next
    INDEX
    Explanations

    real breakouts

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

    scaling, compression, or shearing

    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
     کمپیو
    0.53
    الی
    0.46
    Birthday
    0.44
    Texto
    0.43
    हम
    0.43
     CPU
    0.43
    \'{
    0.43
    INPUT
    0.42
     ofrece
    0.42
    न्ने
    0.42
    POSITIVE LOGITS
     زين
    0.49
     cultivés
    0.48
    厌
    0.47
    udius
    0.46
    olius
    0.46
     것이다
    0.45
     Marin
    0.45
     nasa
    0.45
    ryst
    0.45
     سلي
    0.43
    Activations Density 0.001%

    No Known Activations