© 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. 22285
    Prev
    Next
    INDEX
    Explanations

    hexadecimal codes and constants

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

    The neuron activates on long numeric or hexadecimal sequences (e.g. multi-digit constants or hex dumps) in code or data files.

    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
    ＊＊＊＊
    -1.99
    諼
    -1.94
    蚍
    -1.75
    他们是
    -1.73
    哢
    -1.72
    avatars
    -1.70
    ＝＝＝＝
    -1.66
    tienen
    -1.66
    islam
    -1.65
    ↑↑↑
    -1.64
    POSITIVE LOGITS
    y
    1.95
    6
    1.93
    3
    1.86
    x
    1.84
    ts
    1.84
    J
    1.83
    i
    1.77
    的手
    1.77
    er
    1.70
    1
    1.70
    Activations Density 0.010%

    No Known Activations