© 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. 78161
    Prev
    Next
    INDEX
    Explanations

    custom fields filters

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

    seems effortless, straightforward

    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
     пр
    0.49
     interrupted
    0.48
     cites
    0.46
    ご
    0.43
    標
    0.42
     geared
    0.42
     to
    0.42
     。
    0.41
     Infrastructure
    0.41
    ）：
    0.41
    POSITIVE LOGITS
    Reasoner
    0.42
    ystring
    0.42
     pubb
    0.39
     NSString
    0.39
     তোলেন
    0.39
    ttä
    0.38
     indexing
    0.38
     বিরোধ
    0.38
     مکتی
    0.38
    发行
    0.38
    Activations Density 0.000%

    No Known Activations