© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108822
    Prev
    Next
    INDEX
    Explanations

    complex plane regions

    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
    aparte
    -0.78
    digitalWrite
    -0.75
    fossil
    -0.75
    туаль
    -0.70
     pila
    -0.70
    día
    -0.69
     تقری
    -0.67
    vau
    -0.67
    Meer
    -0.66
    QN
    -0.66
    POSITIVE LOGITS
     plane
    1.45
    plane
    1.25
     half
    1.21
     Plane
    1.16
     planes
    1.15
     region
    1.14
    Plane
    1.13
     strip
    1.11
     regions
    1.09
    strip
    1.05
    Activations Density 0.055%

    No Known Activations