Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 41-GEMMASCOPE-2-RES-65K
    4. 547
    Prev
    Next
    INDEX
    Explanations

    sexual assault

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_width_65k_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
    LPTMR
    0.66
    нём
    0.59
     Federico
    0.57
     सूत्रकृ
    0.56
     javac
    0.55
     hati
    0.55
    ">⁢</
    0.54
    ૈય
    0.53
    شرات
    0.53
     fdPar
    0.53
    POSITIVE LOGITS
     rape
    1.86
     Rape
    1.78
     sexual
    1.52
    rape
    1.46
     raped
    1.46
     Sexual
    1.45
    Sexual
    1.41
     raping
    1.30
     SEXUAL
    1.28
    sexual
    1.26
    Activations Density 0.173%

    No Known Activations