© 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. 2902
    Prev
    Next
    INDEX
    Explanations

    list item assignments

    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
    Negative Logits
    囟
    0.29
    salaryfrom
    0.28
     précise
    0.28
     bonnes
    0.27
     antennes
    0.27
     областях
    0.27
     vattum
    0.27
    </bbox>
    0.26
    yatiti
    0.26
     esigen
    0.26
    POSITIVE LOGITS
    ↵
    0.44
    .
    0.34
    G
    0.32
    T
    0.32
    A
    0.32
    create
    0.31
     the
    0.31
    ag
    0.30
    android
    0.30
    std
    0.30
    Activations Density 0.337%

    No Known Activations