© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 55785
    Prev
    Next
    INDEX
    Explanations

    months, seasons, and time periods

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

    The neuron chiefly activates on numeric tokens (digits and numbers) 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_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
     dziś
    -1.05
     Topf
    -1.05
     сейчас
    -1.05
    streams
    -1.03
     trabajador
    -0.94
     domani
    -0.94
    inę
    -0.93
    大概
    -0.93
    culoskeletal
    -0.91
     Schilder
    -0.91
    POSITIVE LOGITS
     July
    1.90
     June
    1.84
     April
    1.82
     January
    1.80
     August
    1.80
     October
    1.77
     November
    1.71
     February
    1.66
     September
    1.61
     March
    1.59
    Activations Density 0.055%

    No Known Activations