© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113999
    Prev
    Next
    INDEX
    Explanations

    hexadecimal digits or b/B

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

    the hexadecimal character 'b' in technical data files.

    oai_token-act-pair · claude-4-5-sonnet
    Triggered by @bfgcn7frf5

    The neuron activates on hexadecimal byte tokens (e.g., multi‐digit hex numbers) in code or data dumps.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    濑
    -2.19
     itſelf
    -2.17
     came
    -2.16
     goes
    -2.14
    鱟
    -2.11
     for
    -2.11
     comes
    -2.09
    櫪
    -2.09
     Cocina
    -2.08
    疍
    -2.08
    POSITIVE LOGITS
    5
    3.53
    1
    3.27
    You
    2.98
    3
    2.94
     vorigen
    2.88
    7
    2.88
     Hinblick
    2.86
    6
    2.78
    9
    2.77
     selben
    2.66
    Activations Density 0.019%

    No Known Activations