© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29927
    Prev
    Next
    INDEX
    Explanations

    sexual pleasure and gratification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    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
    Nad
    0.38
     SDI
    0.37
     matéri
    0.36
     Material
    0.36
     দত্ত
    0.35
     TDI
    0.35
     inmobili
    0.35
    ྕ
    0.35
    คร
    0.35
     सम्प
    0.35
    POSITIVE LOGITS
     pleasure
    1.84
     Pleasure
    1.57
     pleasures
    1.48
     prazer
    1.40
     plaisir
    1.39
     pleasurable
    1.38
     satisfaction
    1.25
     gratification
    1.20
     grat
    1.16
     piacere
    1.13
    Activations Density 0.022%

    No Known Activations