© 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. 67509
    Prev
    Next
    INDEX
    Explanations

    accessories and product ranges

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

    profanity

    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
     밝혔
    0.42
     diffé
    0.41
    明的
    0.41
    髒
    0.39
    じた
    0.39
     convirt
    0.39
     intervening
    0.38
     archaic
    0.38
     prossimo
    0.38
     jedną
    0.38
    POSITIVE LOGITS
    zinho
    0.49
    ấy
    0.46
    Range
    0.46
    u
    0.46
     घ्यावी
    0.45
     रेंज
    0.45
     पुस्तिका
    0.44
     دقیق
    0.44
     отделение
    0.43
    有多少
    0.43
    Activations Density 0.001%

    No Known Activations