© 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. 22-GEMMASCOPE-RES-131K
    7. 12609
    Prev
    Next
    INDEX
    Explanations

    error handling code

    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
    chaise
    -1.15
    chemise
    -1.12
    kimono
    -1.08
    levis
    -1.02
    seiko
    -1.00
    valentino
    -0.98
    isca
    -0.98
    afka
    -0.96
    modity
    -0.93
    athl
    -0.92
    POSITIVE LOGITS
     full
    0.90
     tried
    0.88
     tries
    0.88
     проще
    0.83
     getting
    0.82
    ディー
    0.82
     ended
    0.82
    静态
    0.80
    donde
    0.79
     terzo
    0.78
    Activations Density 0.001%

    No Known Activations