© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39578
    Prev
    Next
    INDEX
    Explanations

    blue and its contexts

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

    The neuron activates specifically on occurrences of the color name “blue.”

    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
    lgari
    -2.88
    錞
    -2.69
    袿
    -2.64
    ↵↵
    -2.61
    鯔
    -2.61
    臙
    -2.53
    躂
    -2.47
    但却
    -2.30
    发挥
    -2.30
    榀
    -2.25
    POSITIVE LOGITS
    $
    2.77
    2
    2.52
    you
    2.52
    UCIÓN
    2.52
    with
    2.48
    You
    2.42
     You
    2.28
     octombrie
    2.27
    8
    2.25
     Schiffe
    2.23
    Activations Density 0.027%

    No Known Activations