© 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. 103059
    Prev
    Next
    INDEX
    Explanations

    ISBN or numerical codes

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

    The neuron activates on numeric tokens—sequences of digits such as page counts, ISBN numbers, prices, and other multi‐digit 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
     that
    -1.04
     of
    -0.94
     yakni
    -0.93
     by
    -0.88
     nowadays
    -0.86
     Therefore
    -0.84
     Capacidad
    -0.83
     about
    -0.81
     Simplemente
    -0.81
    ÈME
    -0.80
    POSITIVE LOGITS
     OCLC
    1.20
    Lebih
    0.99
    Informasi
    0.98
     véri
    0.97
    Kelebihan
    0.95
    keits
    0.93
    Skor
    0.92
    窣
    0.92
    Vors
    0.91
    Купить
    0.91
    Activations Density 0.002%

    No Known Activations