© 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. 22-GEMMASCOPE-RES-131K
    7. 95582
    Prev
    Next
    INDEX
    Explanations

    code block endings or definitions

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

    The main thing this neuron does is detect numeric literals (numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     mitu
    -1.04
    VERSION
    -0.93
    طلحات
    -0.90
     namens
    -0.90
    THE
    -0.90
    服务
    -0.89
     from
    -0.88
    Version
    -0.84
     Tomaten
    -0.84
    Former
    -0.84
    POSITIVE LOGITS
     ques
    0.95
    FUENTES
    0.94
     entstanden
    0.92
     estarán
    0.92
    árias
    0.92
    modificar
    0.91
    shub
    0.88
     daarbij
    0.88
     ciò
    0.88
    filé
    0.87
    Activations Density 0.034%

    No Known Activations