© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 100023
    Prev
    Next
    INDEX
    Explanations

    sexuality and relationships

    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
    NumConst
    0.50
    韓
    0.50
     unsafe
    0.48
    körper
    0.48
    ಮಾಣ
    0.48
     caregiver
    0.47
     liquors
    0.45
    ಳ
    0.45
    髏
    0.45
    αρ
    0.45
    POSITIVE LOGITS
     Previously
    0.47
     Admit
    0.47
     Expl
    0.47
     Seven
    0.46
     Porn
    0.46
     \
    0.46
    ↵↵
    0.46
     Purple
    0.45
     Excellent
    0.44
     준
    0.44
    Activations Density 0.022%

    No Known Activations