© 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. 32603
    Prev
    Next
    INDEX
    Explanations

    dates or times

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

    dates and times separators

    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
     بودم
    0.43
     otot
    0.43
    ம்தா
    0.43
     egyszer
    0.42
    [multimodal]
    0.41
    关键词
    0.41
     Коро
    0.41
     reconnu
    0.41
     öğretmen
    0.41
     pédagog
    0.40
    POSITIVE LOGITS
     proceeding
    0.39
    amp
    0.38
     言っ
    0.38
    หล
    0.38
    Candy
    0.37
    cm
    0.37
    ŭ
    0.37
    tw
    0.37
     चले
    0.37
     fflush
    0.37
    Activations Density 0.020%

    No Known Activations