© 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. 20888
    Prev
    Next
    INDEX
    Explanations

    modular forms and tree

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

    mathematical and academic terms

    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
    ே
    0.41
     $
    0.40
    ;;
    0.40
     исходя
    0.39
    a
    0.38
    As
    0.38
    .$
    0.38
    かる
    0.38
    র্তি
    0.38
     मात्रा
    0.37
    POSITIVE LOGITS
    ِي
    0.45
     Federación
    0.43
    اني
    0.43
    ング
    0.41
    ني
    0.41
    يديو
    0.40
    ंग
    0.40
     SINGH
    0.39
    夥伴
    0.39
     Navidad
    0.39
    Activations Density 0.000%

    No Known Activations