© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81443
    Prev
    Next
    INDEX
    Explanations

    ball and associated contexts

    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
    ’
    -0.83
     hed
    -0.81
     grüne
    -0.75
     الفن
    -0.75
    if
    -0.75
    olstein
    -0.73
     versteht
    -0.71
    NATURE
    -0.71
    imported
    -0.71
    Catatan
    -0.71
    POSITIVE LOGITS
     ball
    1.47
     Ball
    1.45
     BALL
    1.30
    gown
    1.23
    istics
    1.21
    Ball
    1.20
     bearings
    1.13
    ball
    1.07
     balls
    1.06
     球
    1.06
    Activations Density 0.017%

    No Known Activations