© 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. 108138
    Prev
    Next
    INDEX
    Explanations

    removed from, monitor blood, snorkeling experience

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

    flow, areas, indicates, pinch, water, Dan, blueprint

    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
    usuarios
    0.50
    personas
    0.47
    r
    0.46
     Usuarios
    0.45
    os
    0.45
    спу
    0.43
    produtos
    0.43
    ficha
    0.43
    монт
    0.43
    ס
    0.43
    POSITIVE LOGITS
     Bondi
    0.52
     áp
    0.51
     McDonald
    0.50
    商業
    0.49
    ^{(
    0.49
     McDonalds
    0.49
     markedly
    0.48
    橫
    0.47
    _{(
    0.47
     ladd
    0.47
    Activations Density 0.000%

    No Known Activations