© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 4192
    Prev
    Next
    INDEX
    Explanations

    sexual and explicit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
     農
    0.88
     громадян
    0.84
     Linguistics
    0.83
     Wordsworth
    0.83
     наук
    0.83
    蔥
    0.82
     عدالت
    0.80
    灾
    0.79
    魯
    0.79
     tarix
    0.77
    POSITIVE LOGITS
     erotic
    2.50
     sexual
    2.43
     sensual
    2.23
     sexually
    2.21
     Sexual
    2.17
     сексуа
    2.12
     seksual
    2.10
    Sexual
    2.05
     sexu
    1.97
     sexuality
    1.95
    Activations Density 1.511%

    No Known Activations