© 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. 41818
    Prev
    Next
    INDEX
    Explanations

    quick methods

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

    listing or descriptions

    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
    кус
    0.54
    ة
    0.45
     حالات
    0.44
    История
    0.44
     வரலா
    0.44
    Mounted
    0.44
     vlast
    0.43
    ים
    0.43
    اتر
    0.43
    楪
    0.43
    POSITIVE LOGITS
    डमी
    0.47
    spl
    0.44
    roger
    0.43
     superflu
    0.42
     alphan
    0.42
     notar
    0.42
     screwing
    0.42
     ओर
    0.41
    rz
    0.41
     spher
    0.41
    Activations Density 0.000%

    No Known Activations