© 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. 135265
    Prev
    Next
    INDEX
    Explanations

    Polish syllables and 'discharge hole'

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

    manga, video games, anime

    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
     sweat
    0.48
     곧
    0.46
     Themes
    0.46
     देर
    0.44
     सरकार
    0.43
     sweating
    0.42
     sarkar
    0.42
     deter
    0.42
     Sweat
    0.42
    γε
    0.41
    POSITIVE LOGITS
    フィック
    0.49
     সংগীত
    0.48
    úde
    0.47
    sPath
    0.46
    デ
    0.46
     auffi
    0.45
     గ్రామ
    0.45
    তান্ত্রিক
    0.43
    infinite
    0.42
     মানব
    0.42
    Activations Density 0.000%

    No Known Activations