© 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. 10751
    Prev
    Next
    INDEX
    Explanations

    multilingual words and phrases

    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
     that
    -1.91
     any
    -1.31
     before
    -1.28
     new
    -1.27
     those
    -1.27
     also
    -1.26
     many
    -1.24
     may
    -1.24
     k
    -1.22
     our
    -1.17
    POSITIVE LOGITS
     Fotografía
    1.38
    wäsche
    1.29
     Jenis
    1.27
     Sección
    1.27
     allerlei
    1.25
     estadounid
    1.23
     pietre
    1.23
    things
    1.22
     fiscale
    1.21
    yth
    1.19
    Activations Density 0.184%

    No Known Activations