© 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. 102729
    Prev
    Next
    INDEX
    Explanations

    sexual content and sexuality

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

    The neuron fires strongly on occurrences of the root “sexual” (including “sexuality” and related forms).

    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
     pekan
    -0.80
    าล
    -0.79
     ActionBar
    -0.76
     UITableViewCell
    -0.76
    чется
    -0.75
     ENVIRONMENTAL
    -0.75
     roast
    -0.75
    writeTo
    -0.74
    ühne
    -0.74
     feral
    -0.71
    POSITIVE LOGITS
     sex
    2.30
     sexual
    1.90
     Sex
    1.88
     sexuality
    1.74
    Sex
    1.70
     Sexual
    1.63
    sex
    1.55
     Sexuality
    1.51
     SEX
    1.48
    Sexual
    1.44
    Activations Density 0.032%

    No Known Activations