© 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. 130340
    Prev
    Next
    INDEX
    Explanations

    East, ND, dollars

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

    list item introductions

    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
     Straße
    0.50
     Leth
    0.48
    ,”
    0.47
    ~\
    0.46
     spores
    0.46
    ,"
    0.45
     Landes
    0.44
     sutures
    0.44
    .,
    0.43
     Sutherland
    0.43
    POSITIVE LOGITS
     débil
    0.55
     चर्चित
    0.51
     dirigida
    0.51
     actividad
    0.50
    beginTransaction
    0.50
    ﻓ
    0.49
     descuento
    0.49
     dirigido
    0.49
    割引
    0.49
    ドリンク
    0.49
    Activations Density 0.000%

    No Known Activations