© 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. 222555
    Prev
    Next
    INDEX
    Explanations

    shall see, first stab, calls were

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

    code comments and programming keywords

    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
     e
    0.57
     t
    0.50
    0.46
     Zumba
    0.46
     i
    0.46
     Texas
    0.45
     Q
    0.44
     ting
    0.44
     ploy
    0.43
     ie
    0.43
    POSITIVE LOGITS
    畯
    0.56
    гене
    0.55
    лизации
    0.54
    Ста
    0.54
    РО
    0.54
    Disponible
    0.52
    郢
    0.51
    σο
    0.51
    য়
    0.51
    ۴
    0.51
    Activations Density 0.001%

    No Known Activations