© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98744
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers and code snippets

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

    The neuron strongly activates on hexadecimal numeric tokens (especially “0x…” sequences and individual hex digits).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Fall
    -0.91
     fall
    -0.90
    falls
    -0.88
    Fall
    -0.86
     falling
    -0.84
    落
    -0.80
    fall
    -0.77
     fell
    -0.74
    Falling
    -0.73
     み
    -0.73
    POSITIVE LOGITS
     HEX
    0.85
    scrap
    0.84
     hex
    0.82
     hexadecimal
    0.82
    🥠
    0.81
    x
    0.80
    scra
    0.78
     Hex
    0.78
    adhé
    0.77
    irer
    0.76
    Activations Density 0.010%

    No Known Activations