© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 69081
    Prev
    Next
    INDEX
    Explanations

    geographical place names

    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
     mobiliario
    -1.85
     reciclaje
    -1.82
     estacionamiento
    -1.76
     tránsito
    -1.70
     aparcamiento
    -1.68
    cluye
    -1.66
     bautizo
    -1.64
     descuentos
    -1.62
     secado
    -1.59
     sellado
    -1.57
    POSITIVE LOGITS
     at
    1.85
     for
    1.70
    in
    1.69
    In
    1.66
    all
    1.59
     There
    1.56
    ti
    1.48
    o
    1.47
     In
    1.47
     The
    1.44
    Activations Density 0.108%

    No Known Activations