© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7246
    Prev
    Next
    INDEX
    Explanations

    baseball batted averages

    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
     thru
    -1.05
     acima
    -0.84
     門
    -0.84
    أي
    -0.82
     др
    -0.82
    引起的
    -0.79
     ludzi
    -0.78
    痪
    -0.78
     vimos
    -0.78
     blindly
    -0.77
    POSITIVE LOGITS
    substring
    0.95
     fiori
    0.91
    numberOf
    0.90
    getNumberOf
    0.89
     befindet
    0.88
    DESCRIPCIÓN
    0.85
    Considerations
    0.85
    Acerca
    0.84
    weightedMode
    0.84
    RotationOrder
    0.82
    Activations Density 0.001%

    No Known Activations