© 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. 20618
    Prev
    Next
    INDEX
    Explanations

    Spanish computer terms

    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
    s
    -2.23
    Ꮞ
    -1.80
    _
    -1.68
    ers
    -1.63
    蔸
    -1.61
     zudem
    -1.60
    гун
    -1.55
     Konkur
    -1.55
    ums
    -1.54
    不仅
    -1.54
    POSITIVE LOGITS
    鹚
    1.96
    armament
    1.86
    ℟
    1.84
     árboles
    1.79
    ℣
    1.78
     cerámica
    1.77
     tecnologías
    1.77
     computadoras
    1.76
     dispositivos
    1.75
     脸
    1.75
    Activations Density 0.003%

    No Known Activations