© 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. 73618
    Prev
    Next
    INDEX
    Explanations

    father myself, free planning, touch porcelain, waiting respectfully

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

    multilingual punctuation","language identifiers"

    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
    als
    0.52
    t
    0.52
    in
    0.48
     incessantly
    0.48
    து
    0.48
    ែម
    0.48
    ’)
    0.46
     historique
    0.46
     sociocultural
    0.46
     updateConfirm
    0.45
    POSITIVE LOGITS
     pegs
    0.48
    水を
    0.48
    новним
    0.47
     doanh
    0.46
     ση
    0.46
     _{(
    0.45
    ہری
    0.44
    кономски
    0.44
     까
    0.43
    ہی
    0.43
    Activations Density 0.000%

    No Known Activations