© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 476
    Prev
    Next
    INDEX
    Explanations

    sexual 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
    運輸
    0.46
    👜
    0.40
    📦
    0.40
    @{
    0.39
    elivery
    0.38
    誕生
    0.38
     Wrapping
    0.38
     Birthday
    0.37
     SDK
    0.37
    🍀
    0.37
    POSITIVE LOGITS
     pornography
    1.30
     porn
    1.19
     addiction
    1.12
     sexually
    1.09
     Porn
    1.09
     पोर्न
    1.09
     сексуа
    1.03
    porn
    1.02
     sexual
    1.02
     যৌন
    0.97
    Activations Density 0.567%

    No Known Activations