© 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. 74912
    Prev
    Next
    INDEX
    Explanations

    imports and code structure

    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
     c
    0.42
    onces
    0.39
    <strong>
    0.38
     pero
    0.38
     You
    0.38
     Walnut
    0.38
     Lets
    0.37
     .
    0.36
     Problem
    0.36
     Tipo
    0.36
    POSITIVE LOGITS
    ÈRE
    0.42
    lensFlare
    0.38
    रेगा
    0.38
    UnderWater
    0.38
    ிலும்
    0.37
    Leben
    0.37
     fielded
    0.37
     اندر
    0.37
    dU
    0.36
    ডির
    0.36
    Activations Density 0.013%

    No Known Activations