© 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. 116417
    Prev
    Next
    INDEX
    Explanations

    select filter

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

    The neuron strongly activates on numeric tokens—sequences of digits representing measurements, model numbers, years, quantities, or other numeric specifications.

    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
    zieży
    -0.84
    dynam
    -0.75
    DeclareMath
    -0.74
    aacute
    -0.74
     saben
    -0.73
     ahí
    -0.73
     família
    -0.72
     saca
    -0.72
    ناك
    -0.71
     setError
    -0.71
    POSITIVE LOGITS
    actory
    0.94
     Passenger
    0.92
     passenger
    0.88
     hatchback
    0.88
    antry
    0.85
     Passengers
    0.85
    Passenger
    0.83
     榜
    0.81
    itious
    0.81
     стабили
    0.81
    Activations Density 0.013%

    No Known Activations