© 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. 89355
    Prev
    Next
    INDEX
    Explanations

    years, records, display

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

    products, discovery, and measurements

    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
    ДУ
    0.54
     diversos
    0.48
    針
    0.48
     dựa
    0.47
     skupiny
    0.45
    꿰
    0.45
    多様
    0.44
    🚃
    0.44
    एफ
    0.43
    ENERGY
    0.43
    POSITIVE LOGITS
     resent
    0.52
    west
    0.50
     זו
    0.49
     banished
    0.48
     gall
    0.47
    ocia
    0.47
    ronic
    0.45
     самом
    0.45
     had
    0.44
    osition
    0.44
    Activations Density 0.000%

    No Known Activations