© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 68931
    Prev
    Next
    INDEX
    Explanations

    profanity and expletives

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

    The neuron detects strong profanity or swear words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    I
    -2.05
    these
    -1.77
    在家
    -1.75
    0
    -1.75
     )
    -1.73
    of
    -1.63
     misc
    -1.59
    3
    -1.55
     ….
    -1.55
    1
    -1.54
    POSITIVE LOGITS
    ים
    1.98
    ㌘
    1.89
    ↵
    1.88
     Presidencia
    1.70
    kmäler
    1.69
     regno
    1.69
     avenir
    1.68
     habido
    1.66
    髕
    1.66
     espoir
    1.65
    Activations Density 0.008%

    No Known Activations