© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 74560
    Prev
    Next
    INDEX
    Explanations

    refusal of sexual exploitation

    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
    Negative Logits
    s
    0.43
    어를
    0.41
    збе
    0.41
    Popular
    0.39
     чем
    0.39
     цін
    0.38
    스트
    0.38
     Apache
    0.38
    жуть
    0.37
     коммуна
    0.37
    POSITIVE LOGITS
     =)
    0.52
     ligaments
    0.49
     phenotypes
    0.48
     lesions
    0.46
     pathophys
    0.45
     regeneration
    0.45
     atrophy
    0.45
     😊
    0.44
     calibrations
    0.44
     tinnitus
    0.44
    Activations Density 0.018%

    No Known Activations