© 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. 166341
    Prev
    Next
    INDEX
    Explanations

    years, engines, road, board

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

    not required or may have

    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
    guided
    0.55
    v
    0.55
    sorted
    0.53
    x
    0.53
    var
    0.52
    none
    0.52
    i
    0.52
    ي
    0.52
    ρα
    0.51
    cooked
    0.49
    POSITIVE LOGITS
     аксе
    0.54
     tipp
    0.51
     kontinu
    0.50
     หม
    0.49
     essen
    0.48
     volle
    0.47
    Portug
    0.47
     Styling
    0.47
     पक्षों
    0.47
     Dialer
    0.46
    Activations Density 0.000%

    No Known Activations