© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45402
    Prev
    Next
    INDEX
    Explanations

    time periods and durations

    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
    maillot
    -1.52
     other
    -1.42
    一八
    -1.40
     अन्य
    -1.35
    了一眼
    -1.34
     других
    -1.30
     інших
    -1.29
     dvě
    -1.29
     autres
    -1.27
    graphique
    -1.27
    POSITIVE LOGITS
     médicas
    1.51
     científicas
    1.50
     billetes
    1.38
     —
    1.36
    。
    1.34
     или
    1.34
    スタイ
    1.34
     privadas
    1.29
     económicas
    1.28
     decorativas
    1.26
    Activations Density 0.131%

    No Known Activations