© 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. 235126
    Prev
    Next
    INDEX
    Explanations

    abuse or practitioners

    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
    ގައި
    0.41
    Servlet
    0.40
     strange
    0.37
    C
    0.37
    льника
    0.37
    Mineral
    0.37
    曲
    0.37
     Webcam
    0.37
     climatic
    0.37
    сар
    0.37
    POSITIVE LOGITS
    あるいは
    0.52
    または
    0.51
    ada
    0.50
     evita
    0.49
     बहुमत
    0.48
    ي
    0.48
     또는
    0.47
     quienes
    0.46
     பங்கே
    0.46
     ！
    0.46
    Activations Density 0.001%

    No Known Activations