© 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. 10-GEMMASCOPE-RES-131K
    7. 90360
    Prev
    Next
    INDEX
    Explanations

    mobile carriers and services

    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
    '
    -2.80
     provocado
    -2.11
     comprado
    -2.11
     this
    -2.03
     ataupun
    -1.99
     появился
    -1.97
     estampado
    -1.95
     вернулся
    -1.89
     that
    -1.88
     wünsche
    -1.88
    POSITIVE LOGITS
    ти
    1.74
    苤
    1.73
    ización
    1.70
    鲞
    1.68
    OUTUBE
    1.68
    whose
    1.66
    kan
    1.64
    bija
    1.63
    炱
    1.62
    ⢓
    1.59
    Activations Density 0.004%

    No Known Activations