© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 29935
    Prev
    Next
    INDEX
    Explanations

    sexual content and related concepts

    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
     kuv
    0.51
     Kuv
    0.44
     Brid
    0.44
    ו
    0.43
    п
    0.43
    io
    0.42
    ential
    0.42
    Brid
    0.42
     Cue
    0.42
     แบ่ง
    0.41
    POSITIVE LOGITS
     procé
    0.50
     alcohols
    0.48
    ᱽ
    0.48
     उत्सव
    0.47
    渗透
    0.47
     détecter
    0.46
     ál
    0.46
     discontinue
    0.46
     felonies
    0.46
     cinquième
    0.46
    Activations Density 0.004%

    No Known Activations