© 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. 34-GEMMASCOPE-RES-131K
    4. 103504
    Prev
    Next
    INDEX
    Explanations

    trailer parts and repairs

    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
     Mina
    -0.79
     facturas
    -0.78
     prog
    -0.74
    REVIEW
    -0.73
     Hou
    -0.73
    sps
    -0.72
     variados
    -0.72
     revisión
    -0.71
    rófono
    -0.71
    窗外
    -0.71
    POSITIVE LOGITS
     Dexter
    1.00
     lights
    0.94
     axles
    0.93
    Dexter
    0.89
     École
    0.80
     axle
    0.78
     hubs
    0.76
     santuario
    0.76
     Jerzy
    0.73
     Jardín
    0.73
    Activations Density 0.013%

    No Known Activations