© 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. 210440
    Prev
    Next
    INDEX
    Explanations

    buy button

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

    Rust I/O operations

    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
     eliminated
    0.48
     ਦ
    0.46
    淘汰
    0.45
    ိတ်
    0.44
     ユニ
    0.44
    든지
    0.44
    NSIndexPath
    0.44
    ränkt
    0.44
     произ
    0.43
     première
    0.43
    POSITIVE LOGITS
    ics
    0.45
    2
    0.45
    fas
    0.44
    henko
    0.44
    blasts
    0.43
    पद
    0.43
    standen
    0.43
     americ
    0.42
    अमेर
    0.42
    komen
    0.42
    Activations Density 0.001%

    No Known Activations