© 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. 109920
    Prev
    Next
    INDEX
    Explanations

    DIY or single roles

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

    short distance and releases

    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
     galvanized
    0.51
    ли
    0.51
     virtualization
    0.48
     totaled
    0.47
     wearing
    0.45
    َس
    0.44
     capitalized
    0.44
     tenor
    0.43
     bicovariant
    0.42
     coalesce
    0.42
    POSITIVE LOGITS
    defin
    0.56
    pizza
    0.52
    på
    0.46
    .'/
    0.46
     ஹெ
    0.46
    DIY
    0.45
    🍯
    0.45
    hah
    0.44
     diy
    0.44
    går
    0.44
    Activations Density 0.001%

    No Known Activations