© 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. 104312
    Prev
    Next
    INDEX
    Explanations

    times and places

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

    The neuron fires on numeric tokens (digits, years, dates, 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
     their
    -1.16
     will
    -1.16
     have
    -1.09
     this
    -1.08
     अपने
    -1.00
     its
    -0.98
     своей
    -0.96
     that
    -0.96
     doing
    -0.91
    以及
    -0.90
    POSITIVE LOGITS
    颜值
    1.13
     моего
    1.10
    Život
    1.01
     يتيمه
    1.00
     copias
    1.00
     demandent
    1.00
     توسط
    0.98
     называется
    0.95
    ENTON
    0.95
     according
    0.94
    Activations Density 0.134%

    No Known Activations