© 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. 17460
    Prev
    Next
    INDEX
    Explanations

    multi-lingual identification

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

    Corn starch, smooth surface, full bangs

    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
    ダメージ
    0.43
     डिमांड
    0.38
    榱
    0.38
    처리
    0.38
     MAIN
    0.37
    先进
    0.37
    压
    0.37
    壓
    0.37
    最初
    0.37
     પાડ
    0.37
    POSITIVE LOGITS
     mêmes
    0.45
     leisten
    0.45
     έχουν
    0.44
     gleiche
    0.43
     possono
    0.43
     confusión
    0.43
    पत्र
    0.42
     មាន
    0.42
     accro
    0.42
     nejsou
    0.42
    Activations Density 0.000%

    No Known Activations