© 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. 34-GEMMASCOPE-RES-131K
    7. 82541
    Prev
    Next
    INDEX
    Explanations

    month year dates

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

    The neuron is triggered by numeric tokens (e.g. version numbers, dates, years, and other multi-digit numeric values) in code comments and headers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    昔から
    -1.01
     which
    -0.98
     and
    -0.96
    前から
    -0.92
    您
    -0.90
    ımda
    -0.89
    Опис
    -0.89
     Poliz
    -0.88
     in
    -0.88
     or
    -0.87
    POSITIVE LOGITS
     revisions
    1.27
     ſer
    1.17
    ∊
    1.06
     cerveau
    1.02
    hauled
    1.01
     versiones
    1.00
     ersetzt
    0.98
    捗
    0.98
     Chriftian
    0.96
    even
    0.96
    Activations Density 0.101%

    No Known Activations