© 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. 22-GEMMASCOPE-RES-131K
    4. 130609
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on sequences of hexadecimal digits—i.e. characters in long ID strings such as GUIDs/UUIDs.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    UUIDs and GUIDs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     on
    -1.65
     in
    -1.63
     without
    -1.41
     but
    -1.38
     with
    -1.26
     could
    -1.20
     did
    -1.13
     varias
    -1.13
     проблеми
    -1.11
    GameState
    -1.08
    POSITIVE LOGITS
     disposiciones
    1.28
     GAO
    1.12
    뭄
    1.05
     понадобится
    1.00
    辊
    1.00
    ちゃった
    1.00
    aguer
    1.00
     complejos
    0.98
     convoy
    0.98
     снимки
    0.98
    Activations Density 0.007%

    No Known Activations