© 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. 51129
    Prev
    Next
    INDEX
    Explanations

    pornography, sexually explicit material

    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
     pokuš
    0.48
    щенко
    0.48
     faker
    0.46
     Crack
    0.46
    ᓘ
    0.45
     procur
    0.44
     budgets
    0.44
     procuring
    0.44
     much
    0.43
     bookshelves
    0.43
    POSITIVE LOGITS
    ้า
    0.53
    re
    0.51
    unit
    0.49
    ra
    0.48
    และความ
    0.48
    ம்
    0.48
    nearest
    0.47
    c
    0.46
    tracked
    0.46
    m
    0.46
    Activations Density 0.001%

    No Known Activations