© 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. 40-GEMMASCOPE-2-RES-262K
    7. 220271
    Prev
    Next
    INDEX
    Explanations

    level, you, fragmentation, haven, inheritance

    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_40_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
    人形
    0.41
    owel
    0.38
    +}$
    0.37
     require
    0.36
    arlings
    0.36
    无奈
    0.35
    icer
    0.35
     Welch
    0.34
    追い
    0.34
     ($
    0.34
    POSITIVE LOGITS
     consensual
    0.45
    ității
    0.42
     Rajya
    0.42
     rhs
    0.42
     ஜீய
    0.42
     jo
    0.41
    Peru
    0.41
     சிவா
    0.40
    ِم
    0.39
    uttu
    0.39
    Activations Density 0.001%

    No Known Activations