© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59628
    Prev
    Next
    INDEX
    Explanations

    space, acreage, lot, size

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

    This neuron activates on numeric tokens—especially sequences of digits denoting measurements, dimensions, lot sizes, square-footage, dates, or similar quantitative 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
    OCCURRED
    -0.76
    범
    -0.75
    veret
    -0.75
    ząd
    -0.73
    ipient
    -0.71
     assistant
    -0.71
     Jahrgang
    -0.71
    rold
    -0.71
     addresses
    -0.69
    efois
    -0.69
    POSITIVE LOGITS
     size
    0.82
    vsky
    0.75
     آغاز
    0.75
    Contained
    0.74
     размеров
    0.73
    Contato
    0.72
     resize
    0.72
     quarterfinals
    0.71
    acty
    0.71
     Marlene
    0.71
    Activations Density 0.011%

    No Known Activations