© 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. 251565
    Prev
    Next
    INDEX
    Explanations

    terms of service and user liability

    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
    FlashValue
    0.54
     મળી
    0.51
    澧
    0.50
    トー
    0.49
    foto
    0.48
    inqui
    0.47
     gouvernement
    0.47
     Конечно
    0.47
     વધી
    0.47
     руководителя
    0.47
    POSITIVE LOGITS
     phased
    0.47
     a
    0.44
    ,
    0.44
    lfloor
    0.43
     be
    0.43
     odd
    0.43
     d
    0.42
    provides
    0.42
     driven
    0.42
     w
    0.41
    Activations Density 0.000%

    No Known Activations