© 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. 228164
    Prev
    Next
    INDEX
    Explanations

    qualifying nouns and descriptions

    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
     अधिनियम
    0.54
     เรือ
    0.48
     البحر
    0.47
     اجمع
    0.47
     উপর
    0.46
     الأمير
    0.46
     Instit
    0.46
    忤
    0.46
    ungkinkan
    0.45
     اجمعين
    0.45
    POSITIVE LOGITS
     functional
    0.50
    я
    0.49
     kiwi
    0.49
    мато
    0.48
    ம்மா
    0.47
     purified
    0.47
     piano
    0.45
    жка
    0.44
     legume
    0.43
     seed
    0.42
    Activations Density 0.001%

    No Known Activations