© 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. 60105
    Prev
    Next
    INDEX
    Explanations

    profane or foul language

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

    The neuron flags mentions of the use or investigation of offensive or profane words (e.g. slurs, expletives).

    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
     parallax
    -0.77
     yearly
    -0.75
    ウェイ
    -0.75
    othermic
    -0.74
    זי
    -0.73
    illères
    -0.73
    氫
    -0.71
     Wink
    -0.71
    Stateful
    -0.71
    teig
    -0.71
    POSITIVE LOGITS
     swearing
    3.66
     swear
    3.63
     swears
    2.98
     curse
    2.72
     cursing
    2.64
     swore
    2.56
     profane
    2.19
     curses
    2.19
     prof
    2.14
    curse
    2.09
    Activations Density 0.039%

    No Known Activations