© 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. 70773
    Prev
    Next
    INDEX
    Explanations

    sentence boundary

    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
     to
    -1.53
     التالي
    -1.35
     our
    -1.33
    Ś
    -1.33
     zarówno
    -1.29
    brica
    -1.26
    ție
    -1.20
     柄
    -1.18
    iorgio
    -1.16
    thaf
    -1.16
    POSITIVE LOGITS
    .
    1.49
     churras
    1.36
     it
    1.27
    すすめ
    1.23
    Etape
    1.20
    ogues
    1.18
     theyre
    1.16
     bonito
    1.16
     is
    1.16
     הם
    1.14
    Activations Density 0.015%

    No Known Activations