© 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. 131634
    Prev
    Next
    INDEX
    Explanations

    website, conference, Lahore

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

    company astrology

    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
    〇
    0.47
    URN
    0.45
    ючись
    0.45
     Sagan
    0.43
    ULA
    0.41
    麟
    0.41
    哩
    0.41
    奶奶
    0.41
     Lupus
    0.40
     Sash
    0.40
    POSITIVE LOGITS
     overuse
    0.52
    সমূহ
    0.48
     unités
    0.47
     differing
    0.47
    ichte
    0.46
     बेकार
    0.46
    ibilités
    0.46
     argumentative
    0.46
     Sulawesi
    0.46
     inefficient
    0.45
    Activations Density 0.002%

    No Known Activations