© 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. 10-GEMMASCOPE-RES-131K
    7. 104807
    Prev
    Next
    INDEX
    Explanations

    hexadecimal colors like #ffffff

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

    hexadecimal color codes, particularly white (FFFFFF) and similar light colors.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron detects six‐digit 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
     possono
    -2.89
    {
    -2.22
     пользователем
    -2.17
    っています
    -2.09
    麈
    -2.05
    櫪
    -2.03
     può
    -2.03
     pueden
    -1.96
     Selain
    -1.96
    _
    -1.95
    POSITIVE LOGITS
    𓆜
    3.13
    𓋼
    2.63
    ﺲ
    2.59
     برای
    2.53
    çou
    2.50
     cercando
    2.42
    媄
    2.41
    鹇
    2.41
     Jér
    2.34
    鯓
    2.33
    Activations Density 0.004%

    No Known Activations