© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 123424
    Prev
    Next
    INDEX
    Explanations

    depicts sexual acts

    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_262k_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
    తీ
    0.49
    دا
    0.46
     voet
    0.46
    ま
    0.45
    tså
    0.45
    न्त
    0.44
    льна
    0.44
    Axes
    0.44
    лу
    0.43
    тив
    0.42
    POSITIVE LOGITS
     comedies
    0.47
     optimizations
    0.46
    .
    0.45
     Fleurit
    0.44
    arlos
    0.44
    เหล่านี้
    0.43
     preachers
    0.43
     ພວກເຮົາ
    0.42
     homogé
    0.41
    เสมอ
    0.41
    Activations Density 0.007%

    No Known Activations