© 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. 134686
    Prev
    Next
    INDEX
    Explanations

    non-english words

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

    explanation of changes

    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
    GED
    0.43
    GMT
    0.40
    '};
    0.40
    ETA
    0.40
    SDL
    0.40
    }>
    0.39
    怎樣
    0.39
    ولا
    0.39
    وك
    0.39
    GET
    0.39
    POSITIVE LOGITS
     botella
    0.55
     phí
    0.52
     vache
    0.51
     fichero
    0.50
    வ
    0.49
     agak
    0.49
     adı
    0.48
     explan
    0.47
     herramienta
    0.47
     fossa
    0.47
    Activations Density 0.002%

    No Known Activations