© 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. 12986
    Prev
    Next
    INDEX
    Explanations

    colors and associated concepts

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

    The neuron strongly activates on color words (e.g. “blue,” “red,” “green”).

    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
    /
    -1.40
    {
    -1.30
     midt
    -1.30
     what
    -1.23
     ſeveral
    -1.22
    NOT
    -1.21
     impresionantes
    -1.16
     unica
    -1.16
     unico
    -1.15
     does
    -1.12
    POSITIVE LOGITS
     すぎ
    1.36
    青木
    1.32
    Бил
    1.29
    Jaunes
    1.23
    Garantie
    1.22
     verdadero
    1.22
    !"
    1.21
    共演
    1.20
    ropshire
    1.20
     lia
    1.19
    Activations Density 0.026%

    No Known Activations