© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 7562
    Prev
    Next
    INDEX
    Explanations

    foreign script or archaic language

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

    This neuron detects strong profanity, vulgar expletives, and emphatic curse words in text.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     valeur
    0.27
     a
    0.26
    على
    0.25
     vox
    0.24
     to
    0.24
     mere
    0.23
     sentiment
    0.23
    ধবার
    0.23
     que
    0.23
     veneer
    0.23
    POSITIVE LOGITS
     ಇ
    0.28
    icile
    0.27
     בשנת
    0.27
    ประเทศ
    0.27
     სისტ
    0.27
     땅
    0.26
     பராம
    0.26
    ్
    0.25
    ຫລ
    0.25
     고민
    0.25
    Activations Density 0.258%

    No Known Activations