© 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. 47433
    Prev
    Next
    INDEX
    Explanations

    hue, HS Bcolor, color with hue

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

    The neuron fires on numeric tokens, especially numeric literals or constants (e.g. digits and digit‐containing identifiers).

    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
    startAnimation
    -0.78
    ônica
    -0.74
    thag
    -0.70
    Dougall
    -0.70
    VAN
    -0.69
    unate
    -0.68
     térmica
    -0.68
     spéciaux
    -0.67
     recite
    -0.66
    है
    -0.65
    POSITIVE LOGITS
     H
    1.33
     Hue
    1.23
     HSV
    1.13
     hue
    1.08
     Track
    1.05
     h
    1.04
     Hough
    0.98
    Track
    0.96
    Hue
    0.95
     Hugh
    0.91
    Activations Density 0.042%

    No Known Activations