© 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. 64911
    Prev
    Next
    INDEX
    Explanations

    award and winner

    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
    oniec
    -0.84
    ۓ
    -0.74
    zzard
    -0.74
     ہے۔
    -0.73
    perfusion
    -0.73
    GIF
    -0.70
    xically
    -0.69
    offers
    -0.69
    setViewportView
    -0.68
     استنادى
    -0.68
    POSITIVE LOGITS
     winner
    4.16
     award
    4.09
     winning
    3.97
     awards
    3.83
     winners
    3.81
     awarded
    3.59
     Award
    3.33
     Winner
    3.33
    Awards
    3.27
    award
    3.23
    Activations Density 0.192%

    No Known Activations