© 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. 70790
    Prev
    Next
    INDEX
    Explanations

    pronouns and possessives

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

    The neuron is primarily activated by number‐tokens (numerical digits or numeric values) 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
    TypeError
    -0.93
     навіть
    -0.91
    ắc
    -0.89
     даже
    -0.88
     również
    -0.87
    ým
    -0.87
     myös
    -0.86
    реди
    -0.86
    cznej
    -0.85
     перец
    -0.85
    POSITIVE LOGITS
     they
    2.77
     their
    2.27
     themselves
    1.98
     They
    1.95
    他们
    1.88
    他們
    1.85
    Their
    1.76
     loro
    1.69
     Their
    1.66
     mereka
    1.60
    Activations Density 0.072%

    No Known Activations