© 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. 21934
    Prev
    Next
    INDEX
    Explanations

    absolute positioning

    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
    eneration
    0.47
    д
    0.47
    αλ
    0.45
    edge
    0.44
    ذ
    0.43
    tt
    0.43
    ward
    0.43
    isten
    0.42
    ff
    0.42
    د
    0.42
    POSITIVE LOGITS
     Workflow
    0.49
     Likes
    0.48
     Witcher
    0.47
    이며
    0.47
    굵
    0.46
    ıdır
    0.45
    の名前
    0.45
    を務
    0.45
     ไหน
    0.44
     Recuer
    0.44
    Activations Density 0.003%

    No Known Activations