© 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. 187667
    Prev
    Next
    INDEX
    Explanations

    items and categories

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

    specialized labels or identifiers

    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
     YOUR
    0.42
    荖
    0.41
    !),
    0.41
    ুল্য
    0.37
     Franciscan
    0.36
    artan
    0.35
    正如
    0.35
    다라고
    0.35
     μας
    0.35
    anin
    0.34
    POSITIVE LOGITS
    CONTAIN
    0.39
     زمانی
    0.35
     وغیرہ
    0.35
    ۔
    0.35
     تھے۔
    0.34
    Also
    0.34
    QUENCY
    0.33
    ಫ
    0.33
    calculations
    0.33
     آزم
    0.32
    Activations Density 0.005%

    No Known Activations