© 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. 9690
    Prev
    Next
    INDEX
    Explanations

    numbers and case identifiers

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

    The neuron specifically fires on numeric tokens (years, volume/page numbers, etc.) in reference‐style citations.

    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
    frak
    -0.96
    graham
    -0.91
     stratég
    -0.89
    aurora
    -0.88
     mieli
    -0.87
    tapis
    -0.87
    tım
    -0.86
     uye
    -0.86
    loren
    -0.85
    ǵ
    -0.85
    POSITIVE LOGITS
    határoz
    1.02
     csak
    0.98
    uoto
    0.96
    zi
    0.94
     athe
    0.94
     alms
    0.93
    提出了
    0.91
    lended
    0.90
    ula
    0.88
    ropical
    0.87
    Activations Density 0.003%

    No Known Activations