© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 3748
    Prev
    Next
    INDEX
    Explanations

    sexually explicit content

    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_40_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
     環境
    0.48
    環境
    0.44
     आकृति
    0.43
     আবরণ
    0.42
    旸
    0.42
    Data
    0.42
    En
    0.41
     Technologies
    0.41
    Environ
    0.40
    Technologies
    0.40
    POSITIVE LOGITS
     fucking
    0.89
     raping
    0.82
     fuck
    0.82
     Fuck
    0.79
     sexually
    0.77
    😈
    0.77
     filthy
    0.76
     shitty
    0.75
     slut
    0.74
     disgusting
    0.73
    Activations Density 0.427%

    No Known Activations