© 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. 81597
    Prev
    Next
    INDEX
    Explanations

    yaml specific syntax and libraries

    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
    Html
    -0.81
     Html
    -0.80
     الشه
    -0.74
     chrono
    -0.73
     html
    -0.70
    html
    -0.69
    ланд
    -0.68
     saga
    -0.68
     fazla
    -0.68
    orian
    -0.67
    POSITIVE LOGITS
     YAML
    1.44
     yaml
    1.41
    yaml
    1.36
    YAML
    1.18
     dumps
    1.03
    repres
    0.95
     dumping
    0.94
     dump
    0.91
     dumped
    0.91
    repr
    0.89
    Activations Density 0.119%

    No Known Activations