© 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. 10940
    Prev
    Next
    INDEX
    Explanations

    dates and names

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

    The neuron activates on numeric tokens, especially digits representing dates or times.

    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
     our
    -0.96
     of
    -0.93
     şimdi
    -0.93
     among
    -0.90
     but
    -0.88
     создавать
    -0.88
    NSUInteger
    -0.87
     Selb
    -0.87
     cables
    -0.85
     enough
    -0.84
    POSITIVE LOGITS
    amerikanischer
    1.03
     CREAM
    1.02
     emporter
    1.00
    ългария
    0.99
    ophile
    0.99
     ViewHolder
    0.96
     geko
    0.94
     couper
    0.93
     EEUU
    0.93
     gjelder
    0.93
    Activations Density 0.017%

    No Known Activations