© 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. 40133
    Prev
    Next
    INDEX
    Explanations

    authorship

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

    The neuron primarily detects numeric tokens—years, dates, percentages, counts, and other numbers.

    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
    <i>
    -0.79
     both
    -0.79
     Naz
    -0.76
    kara
    -0.74
    mk
    -0.74
    smart
    -0.74
     so
    -0.74
     gave
    -0.73
    proxy
    -0.73
    ggs
    -0.73
    POSITIVE LOGITS
     kulinar
    1.02
    ctical
    0.98
     redaktion
    0.95
     biograf
    0.89
     imprescin
    0.86
     geprü
    0.86
    Specifik
    0.86
    一般的な
    0.86
    שמי
    0.85
     intrepid
    0.85
    Activations Density 0.067%

    No Known Activations