© 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. 41348
    Prev
    Next
    INDEX
    Explanations

    hexadecimal strings, code, identifiers

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

    This neuron detects long sequences of hexadecimal digits (e.g. commit hashes or GUID‐style 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
    鹮
    -2.58
    ’，
    -2.33
    ,’’
    -2.25
     additions
    -2.16
     装着
    -2.06
    ⋙
    -2.05
    
    -2.05
     "
    -2.03
    睺
    -2.00
    啻
    -2.00
    POSITIVE LOGITS
    In
    2.63
    也许
    2.41
    [
    2.20
    e
    2.17
     you
    2.16
    垍
    2.16
    “[
    2.13
     разные
    2.13
    As
    2.05
     genannten
    1.98
    Activations Density 0.015%

    No Known Activations