© 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. 78596
    Prev
    Next
    INDEX
    Explanations

    manufacturer / supplier

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

    Fresnel Equations

    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
     spans
    0.51
    ری
    0.44
    로
    0.44
     isomorphisms
    0.43
     tiềm
    0.43
    З
    0.43
    ქმ
    0.43
     Recursive
    0.43
     Trojans
    0.42
     progressions
    0.41
    POSITIVE LOGITS
     দ্য
    0.50
     монта
    0.50
     концер
    0.49
     जगत
    0.47
     आपण
    0.47
     кух
    0.46
     থাকত
    0.46
    ᠴ
    0.46
    écoute
    0.45
    ceded
    0.44
    Activations Density 0.004%

    No Known Activations