© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72618
    Prev
    Next
    INDEX
    Explanations

    different varieties or types

    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
    peka
    -1.45
    They
    -1.41
     coche
    -1.31
    Another
    -1.28
    裥
    -1.26
     or
    -1.21
    Without
    -1.19
    lless
    -1.19
     mı
    -1.16
     neum
    -1.16
    POSITIVE LOGITS
     poszczegól
    1.45
     varies
    1.34
     różne
    1.18
     réglementation
    1.17
     разных
    1.17
     различ
    1.17
     such
    1.17
    viesa
    1.16
     experts
    1.16
     مختلف
    1.16
    Activations Density 0.229%

    No Known Activations