© 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. 99620
    Prev
    Next
    INDEX
    Explanations

    shape area perimeter

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects Java structural keywords and tokens (e.g. public, class, void, extends, package) used in code declarations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     عک
    -0.83
     errore
    -0.82
     immagine
    -0.81
     photographie
    -0.79
     beneficia
    -0.79
     important
    -0.79
     equivale
    -0.78
    Taurus
    -0.78
     wichtigen
    -0.78
     itemView
    -0.76
    POSITIVE LOGITS
     perimeter
    1.30
     Shape
    1.21
     Area
    1.17
    Perimeter
    1.16
     Perimeter
    1.14
     area
    1.11
    Area
    1.10
    perimeter
    1.08
    Circum
    1.02
     shape
    1.01
    Activations Density 0.011%

    No Known Activations