© 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. 146600
    Prev
    Next
    INDEX
    Explanations

    termination and marine premiere

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

    words or specific terms

    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
     Little
    0.49
    势力
    0.45
     computed
    0.45
     DOM
    0.44
    柰
    0.43
     Catering
    0.43
    jects
    0.43
     अनंत
    0.43
     Laser
    0.42
     وحدة
    0.42
    POSITIVE LOGITS
    рко
    0.52
    ジュ
    0.48
    ヌ
    0.47
    cigarettes
    0.46
     periodistas
    0.46
    藥
    0.45
    舷
    0.45
    bathtub
    0.45
     adhipp
    0.45
    스코
    0.44
    Activations Density 0.000%

    No Known Activations