© 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. 35296
    Prev
    Next
    INDEX
    Explanations

    software libraries and files

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

    software packages and libraries

    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
    剡
    0.54
     दोहरा
    0.51
    計画
    0.50
    嵊
    0.50
    ットン
    0.50
    牛乳
    0.49
    apayati
    0.49
    EnglishMarks
    0.49
    atthena
    0.48
    燔
    0.48
    POSITIVE LOGITS
     libraries
    0.66
     packaged
    0.64
     library
    0.61
     Libraries
    0.60
     DLL
    0.60
     LIBRARY
    0.59
     LIB
    0.59
     packaging
    0.59
    dll
    0.57
     BIN
    0.57
    Activations Density 0.016%

    No Known Activations