© 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. 34840
    Prev
    Next
    INDEX
    Explanations

    plus-minus and reviews

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

    respects

    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
     khoảng
    0.54
    龐
    0.53
    ཌ
    0.53
    あらゆる
    0.52
     منٹو
    0.51
     乀
    0.49
    ዠ
    0.48
     אחר
    0.47
    getCQL
    0.47
     കാലാവ
    0.47
    POSITIVE LOGITS
    ok
    0.54
     respects
    0.53
    ya
    0.51
    ut
    0.50
    rey
    0.48
     says
    0.48
    ق
    0.48
     respectively
    0.48
    it
    0.48
    wet
    0.47
    Activations Density 0.000%

    No Known Activations