© 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. 12475
    Prev
    Next
    INDEX
    Explanations

    readiness for action

    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
     segítség
    -1.94
     cojín
    -1.90
     manguera
    -1.88
     capucha
    -1.85
     umożli
    -1.84
     llavero
    -1.82
     móds
    -1.81
     zwięks
    -1.80
     almohada
    -1.76
     chaqueta
    -1.73
    POSITIVE LOGITS
     to
    8.44
     of
    1.87
     for
    1.86
     berge
    1.52
     打印
    1.47
     bril
    1.45
     barna
    1.37
     防止
    1.37
     模板
    1.35
    to
    1.34
    Activations Density 0.072%

    No Known Activations