© 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. 169779
    Prev
    Next
    INDEX
    Explanations

    languages spoken

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

    acronyms, definitions, what something means

    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
     QuantityOnHand
    0.50
    midnight
    0.47
     낮
    0.46
     맞
    0.43
     prakt
    0.43
     진
    0.43
     추
    0.43
     Boats
    0.43
     তুলেছে
    0.43
     earthqu
    0.42
    POSITIVE LOGITS
    Мак
    0.53
     \
    0.47
    си
    0.46
     desempen
    0.45
    Де
    0.44
    Как
    0.44
    शेखर
    0.44
    ДЕ
    0.44
    зде
    0.44
    upport
    0.43
    Activations Density 0.001%

    No Known Activations