© 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. 70895
    Prev
    Next
    INDEX
    Explanations

    predictions and scholarly contexts

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

    specific types or representations

    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
     suppuration
    0.49
    클
    0.49
     astonishment
    0.49
    ographical
    0.48
    PlatformTarget
    0.46
     ordnance
    0.46
     quotations
    0.46
     incandescent
    0.45
     remboursement
    0.45
    は大
    0.44
    POSITIVE LOGITS
    ora
    0.50
    elser
    0.45
     VERS
    0.43
    ຝ
    0.43
    ्स
    0.43
     fonksiyon
    0.43
     sistemi
    0.42
     不同
    0.42
     เรือ
    0.41
     Sem
    0.41
    Activations Density 0.001%

    No Known Activations