© 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. 139978
    Prev
    Next
    INDEX
    Explanations

    purposes, holding, realized, empty

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

    numbers and government

    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
    рё
    0.56
    ку
    0.54
    re
    0.54
    direction
    0.51
    р
    0.51
    PE
    0.49
    v
    0.48
    padded
    0.47
    B
    0.47
    рок
    0.47
    POSITIVE LOGITS
     empowerment
    0.49
     chemo
    0.47
     transforma
    0.46
     Journalism
    0.44
    िनेशन
    0.44
     whistleblower
    0.44
     ہے۔
    0.43
     Cheval
    0.43
     Common
    0.43
     empower
    0.43
    Activations Density 0.000%

    No Known Activations