© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 21915
    Prev
    Next
    INDEX
    Explanations

    name or path or number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    デフォルト
    0.40
     ум
    0.36
     IOException
    0.35
    Php
    0.35
    默认
    0.35
     애플
    0.34
     ৮
    0.34
    ป์
    0.34
    Pot
    0.34
    ッシュ
    0.34
    POSITIVE LOGITS
     to
    0.50
     να
    0.45
     how
    0.42
     literal
    0.41
     să
    0.41
     để
    0.40
     untuk
    0.40
     number
    0.39
     لم
    0.37
     zu
    0.37
    Activations Density 0.157%

    No Known Activations