© 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. 71033
    Prev
    Next
    INDEX
    Explanations

    other times, partly, instead

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

    carefully crafting, overload Discord, Dr

    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
    ş
    0.41
    约翰
    0.41
    πό
    0.40
    ७
    0.40
    潵
    0.40
     নায়ক
    0.40
     거리
    0.39
     गवर्नर
    0.39
    俶
    0.39
    ड
    0.38
    POSITIVE LOGITS
     suppresses
    0.52
     completes
    0.48
     with
    0.45
     {}'.
    0.45
     takes
    0.44
     subtly
    0.43
     avec
    0.43
     ifelse
    0.43
     chills
    0.43
    residuals
    0.43
    Activations Density 0.001%

    No Known Activations