© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85920
    Prev
    Next
    INDEX
    Explanations

    letters in lists or sequences

    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
     dalamnya
    -1.42
     soru
    -1.42
     coreana
    -1.41
    usions
    -1.33
     براي
    -1.31
     otel
    -1.31
     additional
    -1.27
     bellissimo
    -1.27
    atized
    -1.23
    ENSES
    -1.20
    POSITIVE LOGITS
     \
    1.39
    щет
    1.27
    alagi
    1.27
    ifilm
    1.23
    だが
    1.20
     dacă
    1.19
    ॉप
    1.18
    usak
    1.16
    adari
    1.15
     noiva
    1.14
    Activations Density 0.266%

    No Known Activations