© 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. 34-GEMMASCOPE-RES-131K
    7. 75578
    Prev
    Next
    INDEX
    Explanations

    template url definitions

    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_34/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
     tienda
    -0.82
     הָ
    -0.77
     خاطر
    -0.77
    essler
    -0.74
     seguros
    -0.73
     opts
    -0.73
    カメ
    -0.73
    Reed
    -0.70
    ISY
    -0.70
     Workout
    -0.69
    POSITIVE LOGITS
    fragment
    0.83
    prefetch
    0.73
     patterned
    0.73
    url
    0.72
     fragment
    0.71
    cello
    0.70
    cektir
    0.70
     ERR
    0.69
     pattern
    0.69
    templateUrl
    0.69
    Activations Density 0.040%

    No Known Activations