© 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. 9294
    Prev
    Next
    INDEX
    Explanations

    integrals, logarithms, and sums

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

    limit and integral notation

    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
    лейбол
    0.49
     घेण्यासाठी
    0.47
    ༽
    0.45
    küm
    0.43
     महीना
    0.42
    mayın
    0.42
    ъм
    0.42
     lembut
    0.41
    горь
    0.41
    ОВО
    0.41
    POSITIVE LOGITS
     of
    0.48
     急
    0.46
     {
    0.42
     C
    0.41
     vutta
    0.39
     ofx
    0.38
    InRange
    0.38
     Region
    0.38
    tic
    0.38
     numeric
    0.37
    Activations Density 0.000%

    No Known Activations