© 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. 145295
    Prev
    Next
    INDEX
    Explanations

    attracting the viewer's eye

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

    quantities and rates

    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
    最適
    0.52
    ほど
    0.49
     მაგრამ
    0.46
    ことも
    0.46
    滈
    0.45
    ächer
    0.45
     Umwelt
    0.45
    ounded
    0.44
     Entwick
    0.44
    ющих
    0.44
    POSITIVE LOGITS
     frame
    0.43
     ars
    0.43
     देतात
    0.43
     श्रृंखला
    0.42
     authorise
    0.42
     $("
    0.41
     αυτή
    0.41
     sulphate
    0.41
     hydroly
    0.40
     protestors
    0.39
    Activations Density 0.001%

    No Known Activations