Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 12237
    Prev
    Next
    INDEX
    Explanations

    report offensive content

    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_40_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
    顧客
    0.46
     умолча
    0.44
    䄸
    0.42
    يكل
    0.41
     untested
    0.38
    ensureEqual
    0.38
    жина
    0.37
    gateTime
    0.37
     কল্পনা
    0.37
     免
    0.37
    POSITIVE LOGITS
     Offensive
    0.61
     offensive
    0.60
     Report
    0.59
     flagging
    0.59
    举报
    0.59
     Abuse
    0.58
    Report
    0.57
     offending
    0.57
    Help
    0.56
     Comment
    0.55
    Activations Density 0.004%

    No Known Activations