© 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. 98261
    Prev
    Next
    INDEX
    Explanations

    colors and emphasis

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

    The neuron activates on color names (e.g., red, blue, green) in the text.

    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
     where
    -1.16
     that
    -1.11
     entrambi
    -1.10
     mwenye
    -1.09
    ならではの
    -1.09
    的味道
    -1.03
    grapher
    -1.03
     like
    -1.02
    おわりに
    -1.02
     assolu
    -0.99
    POSITIVE LOGITS
    Gön
    1.24
     nji
    1.20
     leurs
    1.16
     mijn
    1.12
     més
    1.06
     kalori
    1.04
    ıs
    1.04
     profiter
    1.03
    their
    1.02
    特别是
    1.01
    Activations Density 0.003%

    No Known Activations