© 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. 109369
    Prev
    Next
    INDEX
    Explanations

    email suffix or URL domain

    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
     still
    -0.75
    عط
    -0.75
     aktivitet
    -0.73
     in
    -0.71
    TestResult
    -0.71
    rendre
    -0.71
    дир
    -0.71
     McCa
    -0.70
     expert
    -0.70
    witzerland
    -0.70
    POSITIVE LOGITS
    İR
    0.84
    getOptions
    0.83
    苙
    0.81
    Blind
    0.81
    が開
    0.81
     Gato
    0.81
     trast
    0.81
    定義
    0.80
    诘
    0.80
    IVE
    0.79
    Activations Density 0.004%

    No Known Activations