© 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. 34-GEMMASCOPE-RES-131K
    7. 2957
    Prev
    Next
    INDEX
    Explanations

    hatching and dashed lines

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

    The neuron activates on programming tokens that specify styling or graphical‐style properties (e.g. fill color, fill pattern, border style) in code.

    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
     Squeeze
    -0.94
     squeezed
    -0.93
    twist
    -0.88
     squeezing
    -0.88
     squeeze
    -0.77
     Profil
    -0.75
    entric
    -0.73
     sque
    -0.72
    tafel
    -0.72
    okkal
    -0.71
    POSITIVE LOGITS
     hatch
    1.13
     fill
    1.09
     pattern
    1.09
    hatch
    0.96
     hatching
    0.92
    Pattern
    0.92
     Pattern
    0.91
     hatches
    0.90
    Hatch
    0.90
    PATTERN
    0.85
    Activations Density 0.016%

    No Known Activations