© 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. 22-GEMMASCOPE-RES-131K
    7. 130075
    Prev
    Next
    INDEX
    Explanations

    events during last year

    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_22/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
     jedoch
    -0.97
     Junho
    -0.97
     maisha
    -0.96
    公司
    -0.95
    现在的
    -0.94
    ₩
    -0.93
    tider
    -0.91
     bonjour
    -0.91
    蜥
    -0.91
    ленные
    -0.89
    POSITIVE LOGITS
     last
    2.14
     during
    1.94
     in
    1.57
     yesterday
    1.43
     January
    1.42
     between
    1.38
     July
    1.35
     April
    1.33
     último
    1.32
     this
    1.30
    Activations Density 0.060%

    No Known Activations