© 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. 124462
    Prev
    Next
    INDEX
    Explanations

    me to

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

    free, short, creation, HDL, hungry, sweetness

    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
     ሁሉ
    0.46
    ం
    0.45
    굼
    0.44
    йт
    0.43
     ګټ
    0.43
    들이
    0.43
     bốn
    0.43
     начали
    0.43
     множе
    0.42
     мире
    0.42
    POSITIVE LOGITS
     deficit
    0.53
     as
    0.50
     স্বল্প
    0.48
     ž
    0.48
     device
    0.48
     Refs
    0.48
     if
    0.47
     approximates
    0.47
     synchrotron
    0.47
     refract
    0.46
    Activations Density 0.000%

    No Known Activations