© 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. 75047
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

    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
    c
    -1.47
     [
    -1.41
     Does
    -1.27
    ведении
    -1.24
    ri
    -1.23
    tr
    -1.22
     (
    -1.20
     également
    -1.18
     and
    -1.16
     “
    -1.16
    POSITIVE LOGITS
    翾
    1.46
    autorelease
    1.30
    了许多
    1.29
     būs
    1.28
     moeili
    1.27
     dziś
    1.27
     tetrachloride
    1.24
    olverine
    1.24
    ódromo
    1.23
    діа
    1.23
    Activations Density 0.020%

    No Known Activations