© 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. 54248
    Prev
    Next
    INDEX
    Explanations

    sports events and people

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

    sports competitions dynamic action

    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
     Voilà
    0.46
    Xu
    0.45
     behe
    0.44
    Fu
    0.44
    類似
    0.44
    認為
    0.43
    蓄
    0.43
    瘧
    0.42
    HE
    0.41
    OLOGIE
    0.41
    POSITIVE LOGITS
     tijdens
    0.63
     मुकाबला
    0.55
     podczas
    0.55
     lors
    0.55
     विजयी
    0.54
     Football
    0.52
    球员
    0.52
     during
    0.52
    紧
    0.52
     المباراة
    0.50
    Activations Density 0.024%

    No Known Activations