© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 187856
    Prev
    Next
    INDEX
    Explanations

    styles and options

    np_acts-logits-general · gemini-2.5-flash-lite

    foul language detection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵↵
    0.52
    مم
    0.49
    قبال
    0.48
    Een
    0.48
    حض
    0.48
    Appeal
    0.48
    ྃ
    0.47
    ح
    0.46
    婴儿
    0.46
    Montserrat
    0.46
    POSITIVE LOGITS
     食器
    0.47
     soothing
    0.46
     suburban
    0.46
     सर्वाधिक
    0.45
    さを
    0.44
     खूबसूरती
    0.44
     dinn
    0.44
     স্থল
    0.44
     aluminium
    0.44
     geometric
    0.44
    Activations Density 0.001%

    No Known Activations