© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 77739
    Prev
    Next
    INDEX
    Explanations

    offensive or toxic interactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    కుంట
    0.50
    么
    0.46
    striction
    0.44
    র্ড
    0.44
    getServer
    0.44
    রম
    0.43
    RatingDiff
    0.42
     आगाज
    0.42
     চারটি
    0.41
    ట
    0.41
    POSITIVE LOGITS
     perceptible
    0.57
     noticeable
    0.50
     indeks
    0.46
     smells
    0.46
     Są
    0.46
    پس
    0.44
     discursive
    0.43
     impedir
    0.43
     noticeably
    0.43
     reasoned
    0.43
    Activations Density 0.003%

    No Known Activations