© 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. 81568
    Prev
    Next
    INDEX
    Explanations

    news sources or citations

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

    roles, frames, options, support, DMT

    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
    ів
    0.57
    ين
    0.50
    ністю
    0.50
    ξης
    0.47
    ٦
    0.47
    fläche
    0.46
    duction
    0.46
    ẩm
    0.46
    mesi
    0.46
     confidently
    0.46
    POSITIVE LOGITS
     polu
    0.46
     replicas
    0.46
     destroy
    0.46
    )))))
    0.45
     তরফে
    0.45
     creeps
    0.44
     Invalid
    0.44
     Israel
    0.43
     ನಾ
    0.43
    崴
    0.43
    Activations Density 0.000%

    No Known Activations