© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 19817
    Prev
    Next
    INDEX
    Explanations

    profanity following "fucking"

    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_16_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
     ﺍﻟ
    0.86
     ﺍ
    0.79
    ರ
    0.74
    ב
    0.70
    работ
    0.69
    ր
    0.68
    cj
    0.66
    ﻴ
    0.65
    ট
    0.63
    ի
    0.63
    POSITIVE LOGITS
    us
    0.70
     లేదు
    0.66
    <0x80>
    0.64
     refere
    0.62
    is
    0.61
    un
    0.61
    _
    0.61
     a
    0.59
    $<
    0.58
    itev
    0.58
    Activations Density 0.005%

    No Known Activations