© 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. 119411
    Prev
    Next
    INDEX
    Explanations

    exceptions and errors

    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
    {\
    -0.86
    のある
    -0.82
    ŷ
    -0.79
    Dk
    -0.79
    )=>{
    -0.78
    (
    -0.77
    تح
    -0.77
    는
    -0.76
    hoka
    -0.76
     comparación
    -0.75
    POSITIVE LOGITS
    printStackTrace
    1.16
     e
    1.15
     System
    1.01
    System
    0.95
    StringWriter
    0.91
    traceback
    0.86
    e
    0.84
     ex
    0.79
     体育
    0.75
    altezza
    0.74
    Activations Density 0.002%

    No Known Activations