© 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. 60204
    Prev
    Next
    INDEX
    Explanations

    sports official calls

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

    after colon or number

    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
    ló
    0.47
    ◡
    0.47
    '_{
    0.46
    ច្រើន
    0.45
    ˶
    0.45
    ◐
    0.45
    žad
    0.44
    _{\
    0.44
    HAM
    0.44
    ∂
    0.44
    POSITIVE LOGITS
    inary
    0.44
     seres
    0.43
     Oregon
    0.42
     හො
    0.41
     devem
    0.41
     giants
    0.40
     wor
    0.40
    韪
    0.40
     telef
    0.40
     gentlemen
    0.39
    Activations Density 0.000%

    No Known Activations