© 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. 102418
    Prev
    Next
    INDEX
    Explanations

    range, increasing, or equal in

    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
     zaradi
    -1.08
     ángulo
    -1.05
     nutrición
    -1.04
    dentro
    -1.01
     for
    -0.95
     respiración
    -0.94
    拉克
    -0.93
     energías
    -0.92
     ácidos
    -0.92
    وقتی
    -0.90
    POSITIVE LOGITS
     in
    4.75
     σε
    1.27
     In
    1.23
     در
    1.20
     méret
    1.07
     både
    1.04
     във
    1.03
    azienda
    0.95
    in
    0.95
    Both
    0.93
    Activations Density 0.113%

    No Known Activations