© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 78384
    Prev
    Next
    INDEX
    Explanations

    sexual activity and consent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disgusting
    0.47
     escánd
    0.45
     indecent
    0.44
     scandalous
    0.44
     abuses
    0.43
    sein
    0.43
    罵
    0.42
    飕
    0.42
     corruption
    0.42
     affront
    0.41
    POSITIVE LOGITS
    partner
    0.47
    Partner
    0.46
     partner
    0.45
     Partner
    0.42
     tactile
    0.42
     partners
    0.41
    Provider
    0.40
     consent
    0.39
     партне
    0.39
     mutually
    0.39
    Activations Density 0.437%

    No Known Activations