© 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. 130531
    Prev
    Next
    INDEX
    Explanations

    This neuron detects hexadecimal digits (0–9 and a–f) used in CSS color codes.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    questions and page titles

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    จำนวน
    -0.93
     pleaf
    -0.85
     bedeuten
    -0.84
     buque
    -0.83
    に行って
    -0.83
     emerald
    -0.83
    呸
    -0.82
    baric
    -0.82
     bardzo
    -0.82
    icure
    -0.82
    POSITIVE LOGITS
     their
    0.94
    ctrons
    0.93
    annte
    0.93
    ͐
    0.91
    resolve
    0.90
    urek
    0.90
    鍍
    0.87
    ynku
    0.87
     perna
    0.86
    ńska
    0.86
    Activations Density 0.008%

    No Known Activations