© 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. 95540
    Prev
    Next
    INDEX
    Explanations

    spending close, they supply

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

    function design

    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
    पेयी
    0.51
    篑
    0.51
    䣰
    0.50
    䣫
    0.50
    羵
    0.50
    當時
    0.50
    㥆
    0.50
    Unavailable
    0.48
    कंपनी
    0.48
    اہم
    0.48
    POSITIVE LOGITS
    st
    0.54
    u
    0.54
    '
    0.53
    dea
    0.50
    ct
    0.49
    ype
    0.49
    ol
    0.49
    el
    0.48
    c
    0.48
    set
    0.47
    Activations Density 0.000%

    No Known Activations