© 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. 15872
    Prev
    Next
    INDEX
    Explanations

    showing the first

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

    Superyó, Thumos, current amounts

    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
    a
    0.57
    have
    0.53
     B
    0.46
     D
    0.46
     have
    0.46
     Jonas
    0.45
     Luther
    0.45
    Ga
    0.45
     L
    0.44
     SOR
    0.44
    POSITIVE LOGITS
     выбира
    0.54
    फारिश
    0.54
     seguenti
    0.53
     移動
    0.52
    volvimento
    0.52
     ખાસ
    0.52
     अभिव
    0.51
     توسیع
    0.51
    loginfo
    0.51
     ﺍﻟ
    0.51
    Activations Density 0.000%

    No Known Activations