© 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. 54526
    Prev
    Next
    INDEX
    Explanations

    hex color codes `ff` `#ff`

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

    The neuron activates on two‐digit hexadecimal byte values (e.g. “ff”) used in 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_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
     náš
    -1.21
     unn
    -1.20
    Cuidado
    -1.09
     finalizar
    -1.09
     noastră
    -1.06
     позволяют
    -1.05
    もありますが
    -1.02
     episódios
    -1.02
    onets
    -1.02
     mädchen
    -1.02
    POSITIVE LOGITS
     informa
    1.16
    。
    1.15
     not
    1.15
    ✣
    1.13
    ！！
    1.13
     also
    1.07
    ｝
    1.07
    ！！！
    1.05
    ſtra
    1.05
     kini
    1.04
    Activations Density 0.003%

    No Known Activations