© 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. 118312
    Prev
    Next
    INDEX
    Explanations

    numbers containing the digit 1

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

    The neuron strongly activates on numeric tokens (digits, multi‐digit numbers, codes, dates, etc.).

    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
     since
    -0.81
    sə
    -0.81
    çants
    -0.77
     Siddi
    -0.76
    nière
    -0.75
     являются
    -0.75
     спеціаль
    -0.71
    Pork
    -0.71
     łaz
    -0.70
    oinette
    -0.68
    POSITIVE LOGITS
     ailes
    0.81
     Compro
    0.78
     کمک
    0.77
     sopp
    0.75
    IFIC
    0.74
    ...!
    0.74
     quintessential
    0.73
    λί
    0.72
     rapport
    0.71
    参赛
    0.71
    Activations Density 0.006%

    No Known Activations