© 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. 212046
    Prev
    Next
    INDEX
    Explanations

    actions and procedures

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

    joins and scans

    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
     minh
    0.54
     Aarti
    0.50
    長い
    0.49
     längre
    0.48
    λά
    0.47
     محاس
    0.47
    פת
    0.46
    𓐄
    0.46
    鈁
    0.45
    長く
    0.45
    POSITIVE LOGITS
    arello
    0.47
     ব্যান
    0.46
    escence
    0.45
     spez
    0.45
     permettent
    0.44
    intendo
    0.44
     проводят
    0.44
     mediante
    0.44
    anao
    0.44
     nedeniyle
    0.43
    Activations Density 0.000%

    No Known Activations