© 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. 14723
    Prev
    Next
    INDEX
    Explanations

    code components and errors

    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
     by
    -1.45
    这时
    -1.12
     its
    -1.03
     their
    -1.01
     identical
    -0.99
    phans
    -0.97
     Gouver
    -0.96
     collectively
    -0.94
     inny
    -0.93
    を見
    -0.93
    POSITIVE LOGITS
     ہے۔
    1.16
    unción
    1.14
    %;
    1.09
    fatalError
    1.05
    secu
    1.05
     ہیں۔
    1.03
    
    1.03
     yyr
    1.03
    kowych
    1.02
    says
    1.01
    Activations Density 0.012%

    No Known Activations