© 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. 108340
    Prev
    Next
    INDEX
    Explanations

    color code and values

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

    The neuron fires on occurrences of “color” (and closely related variants like “Color” or “fillColor”) in code or XML.

    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
    NSString
    -0.86
     TextInputType
    -0.73
     size
    -0.73
     deutsch
    -0.73
     NSString
    -0.73
    ="@+
    -0.72
    ":"",
    -0.71
     sizes
    -0.70
     recieved
    -0.69
    setImageBitmap
    -0.68
    POSITIVE LOGITS
    getColor
    1.15
     Context
    0.97
    χρι
    0.84
     teint
    0.82
    的颜色
    0.81
     getResources
    0.80
    ῆ
    0.80
     র
    0.79
     kolor
    0.79
     UIColor
    0.79
    Activations Density 0.004%

    No Known Activations