© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108770
    Prev
    Next
    INDEX
    Explanations

    preseason scrimmage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tournaments
    -0.78
     Filler
    -0.75
     Elles
    -0.73
     contractual
    -0.72
    Klu
    -0.70
    AUR
    -0.69
     Overland
    -0.67
    海上
    -0.66
    shelf
    -0.66
    洞
    -0.66
    POSITIVE LOGITS
     scrimmage
    1.64
     intra
    1.39
     int
    1.33
    紅
    1.10
    intra
    1.08
     spring
    1.07
     scrim
    1.00
     Intra
    0.94
    红
    0.94
     simulated
    0.93
    Activations Density 0.027%

    No Known Activations