© 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. 63470
    Prev
    Next
    INDEX
    Explanations

    monitoring local explanatory models

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

    leaders, many, question, voice

    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
    ≾
    0.48
     российских
    0.48
    CurrentImageData
    0.46
    aterdag
    0.46
     europäischen
    0.45
    𝕚
    0.44
    ispielsweise
    0.44
     горных
    0.43
    టన
    0.43
     живело
    0.43
    POSITIVE LOGITS
    lar
    0.50
     :
    0.44
     Figura
    0.43
    tre
    0.43
    广场
    0.43
    :
    0.42
     footpath
    0.41
    ker
    0.41
    ,
    0.41
     (:
    0.41
    Activations Density 0.001%

    No Known Activations