© 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. 3
    Prev
    Next
    INDEX
    Explanations

    initializer with 0

    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
     apprécier
    -1.05
     mesurer
    -1.04
     travaillent
    -1.02
     attirer
    -1.02
     conduire
    -1.02
     lauded
    -1.02
     satisfaire
    -0.99
    provided
    -0.98
     marvelous
    -0.98
     exceedingly
    -0.97
    POSITIVE LOGITS
     which
    1.99
     when
    1.85
     with
    1.73
     because
    1.61
     before
    1.57
     so
    1.52
     new
    1.50
     in
    1.46
     When
    1.45
     Whenever
    1.34
    Activations Density 0.025%

    No Known Activations