© 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. 71391
    Prev
    Next
    INDEX
    Explanations

    what the

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

    AI products and services

    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
     ((
    0.50
     Expected
    0.47
     %)
    0.47
     (
    0.45
     to
    0.43
     GPS
    0.42
     with
    0.42
     Decline
    0.42
    నిక
    0.42
    %
    0.42
    POSITIVE LOGITS
     שני
    0.55
     musique
    0.50
     ከተ
    0.49
    🇫
    0.49
     approfond
    0.48
    ສາມາດ
    0.48
    компа
    0.48
     stronę
    0.48
     courants
    0.48
    ایر
    0.47
    Activations Density 0.001%

    No Known Activations