© 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. 75540
    Prev
    Next
    INDEX
    Explanations

    . jurisdiction intended brings

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

    things inside

    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
    Negative Logits
     teşekkür
    0.50
     Kochubei
    0.49
     Eman
    0.47
    cinoma
    0.45
     gerçekten
    0.44
    HASH
    0.44
     yardımcı
    0.44
    клика
    0.43
    ₕ
    0.43
    inputStream
    0.43
    POSITIVE LOGITS
     térm
    0.43
    órd
    0.42
    setInt
    0.40
    scopes
    0.40
    erm
    0.39
     gameplay
    0.39
     Intell
    0.39
     মাঝারি
    0.39
     soport
    0.39
    冥
    0.39
    Activations Density 0.000%

    No Known Activations