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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69663
    Prev
    Next
    INDEX
    Explanations

    seduction and temptation

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

    The neuron fires on words evoking sexual or erotic seduction.

    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
    at
    -3.27
    </h3>
    -3.02
     they
    -2.95
    </strong>
    -2.88
    ra
    -2.58
    y
    -2.56
     uſed
    -2.47
     '
    -2.34
    。　　
    -2.34
    ):
    -2.33
    POSITIVE LOGITS
     utilisées
    2.34
     炖
    2.27
    ୌ
    2.23
     sartén
    2.17
    狆
    2.16
    akterysty
    2.13
    艫
    2.11
     глазах
    2.11
    ungkinkan
    2.03
     行っ
    2.02
    Activations Density 0.003%

    No Known Activations