© 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. 199097
    Prev
    Next
    INDEX
    Explanations

    steps; sometimes; great; raising; later

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

    fasting, rating, choice, roast, alarms

    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
     কেননা
    0.53
     Интер
    0.45
    Влади
    0.45
    Portada
    0.44
    Becker
    0.44
    тора
    0.44
    форд
    0.44
     fornecer
    0.44
    埃
    0.43
     заявление
    0.43
    POSITIVE LOGITS
    lk
    0.49
     shops
    0.49
    ljena
    0.46
     допуска
    0.45
    grapes
    0.44
    ulkar
    0.43
     lights
    0.43
    wein
    0.42
    at
    0.40
     milliamperes
    0.40
    Activations Density 0.001%

    No Known Activations