© 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. 10-GEMMASCOPE-RES-131K
    7. 60589
    Prev
    Next
    INDEX
    Explanations

    product options and variations

    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_10/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
     would
    -1.89
     will
    -1.87
    Most
    -1.74
     during
    -1.71
     to
    -1.70
     most
    -1.69
     With
    -1.62
     Most
    -1.62
     In
    -1.61
     give
    -1.56
    POSITIVE LOGITS
    躄
    1.52
    merkmale
    1.36
    味噌汁
    1.30
     místa
    1.30
    klart
    1.30
    ᔑ
    1.28
    odeon
    1.28
     inlay
    1.27
     Mbps
    1.27
    ubs
    1.27
    Activations Density 0.043%

    No Known Activations