© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101919
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers

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

    hexadecimal characters in code or data files.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron activates on hexadecimal characters (letters A–F and a–f) within long hex strings.

    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
    
    -2.83
     and
    -2.67
    岀
    -2.30
    💃
    -2.27
     Mitteln
    -2.27
    🤙
    -2.23
     desbloquear
    -2.19
    畀
    -2.19
    mbda
    -2.17
     decorar
    -2.17
    POSITIVE LOGITS
    ↵
    5.31
    9
    3.20
    5
    2.98
    4
    2.83
    7
    2.78
    n
    2.64
    6
    2.48
    1
    2.41
    8
    2.33
    <i>
    2.14
    Activations Density 0.013%

    No Known Activations