© 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. 206982
    Prev
    Next
    INDEX
    Explanations

    reports, county, inside, summer, profound

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

    made null elevations fighting fall growth leads

    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
     garnished
    0.47
     pivoting
    0.45
    𝙖
    0.43
     squaring
    0.43
     রকমের
    0.42
    ahanam
    0.40
     پیروی
    0.40
     예수
    0.40
     ს
    0.40
    باد
    0.40
    POSITIVE LOGITS
    is
    0.55
     объект
    0.52
     молеку
    0.50
     Eigenschaften
    0.48
    лари
    0.47
    ля
    0.46
    जाने
    0.46
     objek
    0.45
    ーツ
    0.45
     الايه
    0.45
    Activations Density 0.000%

    No Known Activations