© 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-65K
    7. 10787
    Prev
    Next
    INDEX
    Explanations

    adult sex 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_31_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
     प्रारंभिक
    0.45
     플
    0.42
    浱
    0.42
     इसरो
    0.40
    úp
    0.40
    İlk
    0.40
    BMP
    0.39
    štu
    0.39
     بي
    0.38
    蕞
    0.38
    POSITIVE LOGITS
     adult
    1.59
    adult
    1.53
     adults
    1.51
     Adult
    1.51
     Adults
    1.48
    Adult
    1.47
     adultes
    1.45
     adulto
    1.42
     adulta
    1.38
     adultos
    1.32
    Activations Density 0.250%

    No Known Activations