© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25605
    Prev
    Next
    INDEX
    Explanations

    historic Indian burial ground

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

    The neuron is detecting SVG (or Android vector) path‐Data commands and their numeric coordinates (e.g. “l,” “c,” “L,” “C,” etc.) in XML vector graphics.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ilerini
    -1.09
    pahan
    -1.04
    ʰ
    -0.97
    ushchev
    -0.97
     useAppContext
    -0.97
    くれた
    -0.95
     josé
    -0.95
    ऎ
    -0.94
    してほしい
    -0.94
    ởi
    -0.94
    POSITIVE LOGITS
     
    1.05
     I
    1.05
     our
    1.04
    er
    0.93
     günstiger
    0.92
     ordentlich
    0.91
     gleiche
    0.89
     aufgenommen
    0.88
    んですが
    0.87
     bewegt
    0.86
    Activations Density 0.002%

    No Known Activations