© 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. 139719
    Prev
    Next
    INDEX
    Explanations

    multiple instances or frequency

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

    actions and media

    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
    us
    0.42
     Ü
    0.42
    f
    0.41
    g
    0.41
    todos
    0.40
    re
    0.40
    cc
    0.40
    biod
    0.40
    Biod
    0.40
    Todos
    0.39
    POSITIVE LOGITS
     broadly
    0.47
     нередко
    0.47
     வழக்கு
    0.45
     numerosas
    0.45
     fréquentes
    0.44
     často
    0.43
    啭
    0.43
     পুস্তকের
    0.42
    频繁
    0.41
     സമ്
    0.41
    Activations Density 0.002%

    No Known Activations