© 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. 169580
    Prev
    Next
    INDEX
    Explanations

    sports terms

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

    text structure burstiness

    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
     coercive
    0.40
     پایین
    0.40
    urah
    0.39
     sobretudo
    0.38
    পুরের
    0.38
     coercion
    0.38
     uptick
    0.37
    🔺
    0.37
     प्रव
    0.36
    帙
    0.36
    POSITIVE LOGITS
    Basketball
    0.51
    basketball
    0.48
     spielte
    0.47
    ｯ
    0.47
     Basketball
    0.46
     hjel
    0.45
    ﾌ
    0.45
    篮球
    0.45
    NFL
    0.44
     basketball
    0.44
    Activations Density 0.002%

    No Known Activations