© 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. 45029
    Prev
    Next
    INDEX
    Explanations

    hex color codes

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

    The neuron fires on the '#' that begins a hex color literal in code.

    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
     resolute
    -2.38
    ・・。
    -2.19
    ̭
    -2.17
     間取り
    -2.09
    蔭
    -2.08
    とある
    -2.06
     noteworthy
    -2.06
     dazzling
    -2.05
    \
    -2.00
    ”
    -1.96
    POSITIVE LOGITS
     COULD
    3.03
    could
    2.61
     Anſ
    2.48
     "#
    2.47
     '#
    2.47
    赑
    2.44
     Provide
    2.39
    凩
    2.38
    龵
    2.28
     TAKE
    2.25
    Activations Density 0.003%

    No Known Activations