© 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. 10-GEMMASCOPE-RES-131K
    7. 128943
    Prev
    Next
    INDEX
    Explanations

    color palettes

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

    This neuron responds to plotting/color‐scale terminology—tokens referring to colorbars, colormaps, palettes, and related scale settings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     about
    -1.80
     Even
    -1.76
     jednod
    -1.75
     That
    -1.72
     It
    -1.71
    呼ば
    -1.70
    gehende
    -1.66
    istungen
    -1.66
     melindungi
    -1.66
     and
    -1.62
    POSITIVE LOGITS
      
    2.16
    '
    2.06
    0
    1.81
     gebra
    1.69
    *
    1.66
    (
    1.60
                
    1.50
    ↵
    1.49
    4
    1.47
    ↵↵
    1.41
    Activations Density 0.004%

    No Known Activations