© 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. 42716
    Prev
    Next
    INDEX
    Explanations

    mathematical notation with integrals

    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
     also
    -1.69
     versioni
    -1.54
    ，”
    -1.43
    !
    -1.36
     事務
    -1.34
     Our
    -1.33
     told
    -1.32
     If
    -1.29
    又要
    -1.28
    ၜ
    -1.28
    POSITIVE LOGITS
    >
    1.45
     équilibre
    1.38
     hadde
    1.34
    ₖ
    1.31
     CiNii
    1.31
     tantos
    1.30
    zdroj
    1.29
     saati
    1.28
     intenciones
    1.28
     course
    1.27
    Activations Density 0.017%

    No Known Activations