© 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. 22-GEMMASCOPE-RES-131K
    7. 34513
    Prev
    Next
    INDEX
    Explanations

    colors

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

    The neuron detects color names (like grey, red, blue, orange) appearing in code or style attributes.

    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
    ,
    -1.17
     various
    -1.09
     a
    -1.09
     not
    -1.03
     as
    -1.01
     &
    -1.00
     in
    -1.00
     it
    -0.99
     how
    -0.98
     so
    -0.96
    POSITIVE LOGITS
     vittoria
    1.28
    」,
    1.24
    orrho
    1.23
    ⠀⠀⠀⠀⠀⠀⠀⠀
    1.23
     entschieden
    1.21
    킁
    1.20
     légèrement
    1.19
     {
    1.18
     modifié
    1.16
    бѣ
    1.15
    Activations Density 0.007%

    No Known Activations