© 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. 164342
    Prev
    Next
    INDEX
    Explanations

    foreign language characters or names

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

    informs thinking

    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
    í
    0.51
     mediator
    0.48
     Mediator
    0.46
     أيض
    0.44
     kter
    0.44
     CHANGE
    0.44
     zmian
    0.44
    是一名
    0.43
     bloque
    0.41
    r
    0.41
    POSITIVE LOGITS
    Не
    0.50
    雅黑
    0.47
    ោធ
    0.45
    াহিয়া
    0.45
     เน
    0.45
     Freizeit
    0.45
    Zhou
    0.44
    Fluor
    0.44
     Shuang
    0.44
     Не
    0.43
    Activations Density 0.000%

    No Known Activations