© 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. 83771
    Prev
    Next
    INDEX
    Explanations

    works with, not permit, target companies

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

    identifying English text

    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
    дование
    0.51
    ijdens
    0.47
     память
    0.47
    щего
    0.47
     общество
    0.46
    휙
    0.46
    дом
    0.46
    음
    0.46
     gente
    0.46
    лая
    0.45
    POSITIVE LOGITS
     Sauer
    0.56
    si
    0.52
    to
    0.52
    ko
    0.51
    tu
    0.51
     Chinn
    0.51
     Selected
    0.50
     As
    0.50
     Hyper
    0.49
     KIM
    0.49
    Activations Density 0.000%

    No Known Activations