© 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. 10-GEMMASCOPE-RES-131K
    7. 13447
    Prev
    Next
    INDEX
    Explanations

    colors and shades

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

    The neuron activates on words naming or describing colors (e.g., red, green, blue, peach, coral, neutrals, shimmers).

    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
     there
    -1.91
    </strong>
    -1.63
     then
    -1.45
     spectateurs
    -1.40
    piecze
    -1.32
     Tides
    -1.32
    ,
    -1.31
     enseignants
    -1.30
     docente
    -1.28
     travailleurs
    -1.25
    POSITIVE LOGITS
     our
    1.87
     или
    1.70
    tauan
    1.52
     otras
    1.50
    するために
    1.46
     atau
    1.44
     zacz
    1.43
    玧
    1.43
     or
    1.40
     شروع
    1.38
    Activations Density 0.043%

    No Known Activations