© 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. 135584
    Prev
    Next
    INDEX
    Explanations

    beginning of stages

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

    set theory difference operator

    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
     يو
    0.52
    聊
    0.52
    긔
    0.48
     인해
    0.47
     ይጠ
    0.46
     谢
    0.45
    통령
    0.44
    식을
    0.44
     의해
    0.44
     Bewertungen
    0.44
    POSITIVE LOGITS
    with
    0.51
    i
    0.50
    two
    0.48
    module
    0.48
    test
    0.47
    mall
    0.46
    work
    0.45
    standard
    0.45
    take
    0.45
    MTV
    0.45
    Activations Density 0.001%

    No Known Activations