© 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. 212890
    Prev
    Next
    INDEX
    Explanations

    stakes, warranty

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

    while / though / but statements

    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
    al
    0.58
     plantings
    0.50
     baking
    0.46
    em
    0.46
     এমন
    0.46
     দক্ষতা
    0.46
    近
    0.46
    el
    0.45
     দক্ষতার
    0.45
     Baking
    0.44
    POSITIVE LOGITS
    เหมือน
    0.47
    โรงแรม
    0.46
    पीरिय
    0.44
    ﻧ
    0.44
     wundersch
    0.44
    صیٰ
    0.44
    ﻟ
    0.43
    หว
    0.43
     همین
    0.42
     شورای
    0.42
    Activations Density 0.000%

    No Known Activations