© 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. 10-GEMMASCOPE-RES-131K
    7. 11644
    Prev
    Next
    INDEX
    Explanations

    ending

    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_10/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
    蚡
    -1.34
     ?,
    -1.30
     powiedzieć
    -1.27
    felizmente
    -1.27
    being
    -1.27
    囖
    -1.27
     techniczne
    -1.23
    ...',
    -1.22
     ſ
    -1.20
    tamment
    -1.20
    POSITIVE LOGITS
     this
    1.52
     of
    1.44
     этих
    1.27
     piccoli
    1.25
     these
    1.24
    英國
    1.22
     цього
    1.16
     gagné
    1.12
     preocupación
    1.11
     インチ
    1.08
    Activations Density 0.028%

    No Known Activations