© 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. 129440
    Prev
    Next
    INDEX
    Explanations

    running or triathlon

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

    function calls and parentheses

    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
     buil
    0.54
    ,
    0.53
     to
    0.49
     migrate
    0.48
     fundraisers
    0.48
     unlock
    0.47
     loca
    0.46
     build
    0.46
     hangers
    0.46
     leaders
    0.46
    POSITIVE LOGITS
    ೬
    0.54
    zebra
    0.53
    ਹੀ
    0.51
    遛
    0.50
    kül
    0.49
    fär
    0.48
    tı
    0.47
    lovl
    0.47
    liter
    0.47
    durch
    0.47
    Activations Density 0.000%

    No Known Activations