© 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
    2. Gemma-3-27B-IT
    3. 53-GEMMASCOPE-2-RES-262K
    4. 15036
    Prev
    Next
    INDEX
    Explanations

    latex, PVC, and lace

    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_53_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
     sdl
    0.44
     fieldwork
    0.43
     peaceful
    0.41
     pleasant
    0.41
    읍
    0.41
     amiable
    0.40
    昍
    0.38
     生活
    0.38
     dispone
    0.38
     disposed
    0.38
    POSITIVE LOGITS
     latex
    0.88
     PVC
    0.77
    PVC
    0.74
     lingerie
    0.73
     neon
    0.72
     Latex
    0.72
     oversized
    0.71
     lace
    0.70
     biker
    0.69
     metallic
    0.67
    Activations Density 0.031%

    No Known Activations