© 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. 81312
    Prev
    Next
    INDEX
    Explanations

    population numbers

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

    The neuron activates on numeric tokens—i.e. numbers conveying measurements, counts, dates, or statistical values.

    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
     destinada
    -1.02
     여러
    -0.98
     banyak
    -0.92
     anklicken
    -0.91
     exclusivamente
    -0.90
    原始内容存档
    -0.90
     niekoľ
    -0.90
     gradualmente
    -0.88
     ďal
    -0.88
     money
    -0.86
    POSITIVE LOGITS
     a
    4.44
     an
    2.20
     prêmio
    1.16
     namorado
    1.05
     einem
    1.04
     einer
    1.03
     herói
    1.00
     jardim
    0.98
     senhor
    0.98
     anderes
    0.97
    Activations Density 0.178%

    No Known Activations