© 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. 216245
    Prev
    Next
    INDEX
    Explanations

    Next up was statement inside email boxes

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

    dialogue, Subject, matches

    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
    Abort
    0.45
    er
    0.45
    Event
    0.44
     استف
    0.44
    Harvest
    0.43
     nghiệm
    0.43
     মান
    0.42
    ,
    0.42
    ing
    0.41
    Dir
    0.41
    POSITIVE LOGITS
     MW
    0.49
    🦑
    0.47
     ScriptInterface
    0.46
     Sincerely
    0.46
     gutes
    0.45
     Spitze
    0.45
     resolvers
    0.44
     ##
    0.44
     Liao
    0.43
     palais
    0.43
    Activations Density 0.001%

    No Known Activations