© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7138
    Prev
    Next
    INDEX
    Explanations

    color white

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

    The neuron fires on color specifications—both named colors and hexadecimal color codes.

    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
     omtrent
    -1.41
     zade
    -1.28
    ServerError
    -1.25
    batis
    -1.20
     antes
    -1.20
    能够
    -1.20
     to
    -1.18
     realmente
    -1.16
     bied
    -1.09
    Pitch
    -1.09
    POSITIVE LOGITS
     white
    1.26
    組み立て
    1.22
    Borrar
    1.20
    飒
    1.19
    解消
    1.15
    white
    1.13
     Romagna
    1.13
    ueba
    1.10
    Ruju
    1.10
    調節
    1.09
    Activations Density 0.036%

    No Known Activations