© 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. 216347
    Prev
    Next
    INDEX
    Explanations

    speed ahead

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

    distinct options or unrelated items

    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
    ،
    0.51
     Excluding
    0.42
    简洁
    0.42
    юк
    0.40
    ین
    0.40
     Dearborn
    0.40
    畑
    0.39
    Android
    0.39
    기가
    0.39
    ，
    0.39
    POSITIVE LOGITS
    uidor
    0.47
    atthe
    0.46
    ()['
    0.46
     uczest
    0.45
     humides
    0.45
     अणुओं
    0.44
     reuniones
    0.43
     publice
    0.43
     pís
    0.43
     प्रतिद्व
    0.42
    Activations Density 0.000%

    No Known Activations