© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 237387
    Prev
    Next
    INDEX
    Explanations

    foreign words, submission details

    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
    ING
    0.63
    d
    0.59
    m
    0.57
    ESS
    0.55
    ISTS
    0.52
    ing
    0.52
    IDE
    0.51
    Ur
    0.50
    IPA
    0.50
    re
    0.50
    POSITIVE LOGITS
     newState
    0.54
     måtte
    0.52
     ஆகியோர்
    0.52
    啻
    0.51
    缱
    0.50
    ・・・。
    0.49
    竴
    0.48
    新人
    0.48
     कृति
    0.47
     Karlsson
    0.47
    Activations Density 0.001%

    No Known Activations