© 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. 252021
    Prev
    Next
    INDEX
    Explanations

    foreign language names

    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
     Enrichment
    0.50
     Harvesting
    0.46
     tributes
    0.45
     Stewardship
    0.45
    няет
    0.44
    _$
    0.44
    omeres
    0.44
     Балтбет
    0.43
     Стаўкі
    0.43
    lc
    0.43
    POSITIVE LOGITS
     Taj
    0.54
    踴
    0.47
     Ně
    0.47
    弟子
    0.46
    羅
    0.46
     Jaff
    0.46
     Jiří
    0.45
     लग्न
    0.45
    輔
    0.44
     রাজ
    0.43
    Activations Density 0.000%

    No Known Activations