© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3495
    Prev
    Next
    INDEX
    Explanations

    sexuality and affairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     മിക
    0.48
    僑
    0.43
    鎳
    0.42
     फेव
    0.40
     инфраструк
    0.40
    Ⴉ
    0.39
     кван
    0.39
    藹
    0.39
     програм
    0.39
     คณิต
    0.38
    POSITIVE LOGITS
     sexually
    1.60
     sexual
    1.56
     Sexual
    1.49
     sexu
    1.45
     যৌন
    1.39
     sexuales
    1.38
     seksual
    1.37
     यौन
    1.36
     сексуа
    1.36
    Sexual
    1.35
    Activations Density 0.212%

    No Known Activations