© 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. 50194
    Prev
    Next
    INDEX
    Explanations

    scrollable UI elements

    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
    geois
    -0.86
     opgenomen
    -0.85
     sicherzustellen
    -0.84
     proberen
    -0.82
     MPR
    -0.82
     presta
    -0.79
     Punkten
    -0.79
     angefangen
    -0.79
    Choisissez
    -0.78
     Departmental
    -0.78
    POSITIVE LOGITS
    setViewportView
    1.30
    VERTICAL
    0.86
     JScrollPane
    0.84
     kons
    0.83
    ковым
    0.83
     клини
    0.82
    тинга
    0.79
    YAxis
    0.78
     TestBed
    0.77
    ÜN
    0.77
    Activations Density 0.001%

    No Known Activations