© 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. 10-GEMMASCOPE-RES-131K
    7. 90879
    Prev
    Next
    INDEX
    Explanations

    prostitution and Mozilla

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

    The neuron detects mentions of prostitution (and related forms like “prostitute” or “prostitution”).

    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
     we
    -3.03
     they
    -2.78
     scrutin
    -2.58
     lament
    -2.47
    ができ
    -2.45
    轳
    -2.42
    樒
    -2.31
    齁
    -2.27
    作品の
    -2.23
    
    -2.23
    POSITIVE LOGITS
    a
    3.31
    m
    3.05
    t
    2.52
    酲
    2.39
    ”?
    2.39
     він
    2.38
    狆
    2.38
    ”;
    2.36
    ”.
    2.27
    ”,
    2.27
    Activations Density 0.009%

    No Known Activations