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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 115914
    Prev
    Next
    INDEX
    Explanations

    butt, ass, arse

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

    The neuron fires strongly on coarse, insulting language—especially “ass”-based profanity (e.g. “kick its ass,” “pain in the ass,” “bad ass,” “asses,” “working her ass off”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sach
    -0.78
    忍受
    -0.77
    довые
    -0.77
     AllMovie
    -0.75
    ışık
    -0.75
    alimenta
    -0.71
    uteur
    -0.70
     mélang
    -0.69
    DEPTH
    -0.69
    worms
    -0.68
    POSITIVE LOGITS
     ass
    3.42
     butt
    2.38
     asses
    2.30
    ass
    2.19
    Ass
    2.02
     arse
    2.00
     ASS
    1.97
     Ass
    1.88
    ASS
    1.73
     Butt
    1.63
    Activations Density 0.014%

    No Known Activations