© 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. 65087
    Prev
    Next
    INDEX
    Explanations

    XML tags and closing brackets

    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
    壃
    0.48
    昙
    0.47
     Fields
    0.47
    끝
    0.44
    ulations
    0.44
    ículas
    0.44
     নিয়ন্ত্র
    0.43
    imals
    0.43
     ત્યારબાદ
    0.43
    $\
    0.43
    POSITIVE LOGITS
     blacksmith
    0.47
     stockpile
    0.46
     sauerkraut
    0.44
     dau
    0.44
     ใคร
    0.43
     verhaal
    0.43
     diez
    0.43
     lettere
    0.43
     tomates
    0.42
     ナイス
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.