© 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. 239799
    Prev
    Next
    INDEX
    Explanations

    possess or institution

    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
    льо
    0.52
    рих
    0.48
    лизации
    0.47
    ريك
    0.47
     adicional
    0.47
    삵
    0.46
    또
    0.46
    그러
    0.46
     simulated
    0.45
     indicador
    0.45
    POSITIVE LOGITS
    institution
    0.65
    att
    0.60
    d
    0.59
    st
    0.56
    vou
    0.56
    yst
    0.55
    living
    0.55
    bi
    0.55
    homme
    0.55
     Simone
    0.54
    Activations Density 0.000%

    No Known Activations