© 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. 98604
    Prev
    Next
    INDEX
    Explanations

    month/year formatting

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

    The neuron is tuned to detect standalone numeric digits (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_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
     היתה
    -0.82
     sophisticated
    -0.81
     مؤرشف
    -0.80
    FORMANCE
    -0.80
     muelle
    -0.79
    曲は
    -0.79
     teenage
    -0.77
     monasterio
    -0.76
    tehende
    -0.76
    不清
    -0.76
    POSITIVE LOGITS
     here
    1.02
     obiettivo
    0.93
     orizz
    0.89
     его
    0.86
    palen
    0.85
     れ
    0.83
     ambienti
    0.82
     tartış
    0.82
     crater
    0.81
     enthalten
    0.79
    Activations Density 0.001%

    No Known Activations