© 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. 103445
    Prev
    Next
    INDEX
    Explanations

    sexuality

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

    The neuron is specialized in detecting occurrences of the word “sexuality” (and closely 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_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
     uſed
    -2.28
    ﹕
    -2.27
     wens
    -2.23
     uses
    -2.13
    
    -2.11
     夜景
    -2.09
    ar
    -2.09
     was
    -2.05
     pioneered
    -2.03
     immobili
    -2.02
    POSITIVE LOGITS
    .
    3.02
    ſu
    2.52
                
    2.38
    蛱
    2.22
    硯
    2.22
     woes
    2.14
    𓁹
    2.09
     Ergänzung
    2.09
     anstatt
    2.08
    蹉
    2.05
    Activations Density 0.002%

    No Known Activations