© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 29919
    Prev
    Next
    INDEX
    Explanations

    item number or category

    np_acts-logits-general · gemini-2.5-flash-lite

    items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _
    0.85
    (
    0.84
     be
    0.82
    什么
    0.73
    -
    0.71
    কে
    0.71
    $
    0.68
    ك
    0.66
    ㅎ
    0.65
    ली
    0.64
    POSITIVE LOGITS
     Item
    1.23
     item
    1.13
     ITEM
    1.13
     newItem
    1.12
     getItem
    1.11
     onItem
    1.10
     आइटम
    1.06
     itemList
    1.06
     Items
    1.05
     항목
    1.05
    Activations Density 0.035%

    No Known Activations