© 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. 13173
    Prev
    Next
    INDEX
    Explanations

    it is / it should

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

    documentation and factual descriptions

    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
    éo
    0.47
    ie
    0.45
    ur
    0.45
    un
    0.44
    op
    0.44
    ulen
    0.44
    ok
    0.43
     A
    0.43
    let
    0.42
    at
    0.42
    POSITIVE LOGITS
     亠
    0.61
     Elytres
    0.58
    驩
    0.58
    <unused94>
    0.56
    䐪
    0.56
     நடவடிக்க
    0.55
     極
    0.55
     言っ
    0.55
    ﾙ
    0.55
     miễn
    0.54
    Activations Density 0.000%

    No Known Activations