© 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. 200795
    Prev
    Next
    INDEX
    Explanations

    medical terms and abbreviations

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

    scientific and technical terms

    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
    Option
    0.47
    閫
    0.47
     Garza
    0.46
    Bomb
    0.45
     Боль
    0.45
    Shipping
    0.45
     courbe
    0.44
     설계
    0.44
     Folding
    0.44
     здесь
    0.43
    POSITIVE LOGITS
     underestimates
    0.47
    tres
    0.46
    g
    0.46
    ד
    0.46
    អស់
    0.45
    tu
    0.45
    جب
    0.44
    شاف
    0.43
    dafx
    0.43
    br
    0.42
    Activations Density 0.000%

    No Known Activations