© 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. 103486
    Prev
    Next
    INDEX
    Explanations

    a new item

    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
    нов
    -0.82
    <>("
    -0.80
    onyme
    -0.78
     relie
    -0.77
    dagangan
    -0.76
     structures
    -0.76
    ógy
    -0.76
    濬
    -0.76
    لت
    -0.75
    ുക
    -0.75
    POSITIVE LOGITS
     programmable
    1.28
     portable
    1.15
     waterproof
    1.02
     ultrasonic
    0.98
     infrared
    0.97
    Portable
    0.94
     Wii
    0.94
     Yamaha
    0.93
     enlar
    0.92
    bogen
    0.91
    Activations Density 0.069%

    No Known Activations