© 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. 75394
    Prev
    Next
    INDEX
    Explanations

    points and risk

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

    factors to consider

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Q
    0.51
    Dictionary
    0.50
    Cel
    0.50
    Configure
    0.48
    Activate
    0.48
    ক
    0.48
    Y
    0.48
    Energy
    0.47
    Vas
    0.47
    Help
    0.47
    POSITIVE LOGITS
    د
    0.52
     발견
    0.51
    溅
    0.49
    пия
    0.49
    яви
    0.48
     fakta
    0.48
    affine
    0.48
    ิ่ม
    0.48
     соревнования
    0.48
    나가
    0.47
    Activations Density 0.000%

    No Known Activations