© 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. 117921
    Prev
    Next
    INDEX
    Explanations

    planning, heritage, national

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

    The neuron strongly activates on numeric quantities—especially multi‐digit numbers and large figures.

    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
    ɬ
    -0.80
     Lawyer
    -0.79
    generational
    -0.76
     leeftijd
    -0.75
     băng
    -0.74
    訖
    -0.74
    remaining
    -0.73
    ってみました
    -0.72
    alya
    -0.71
    pax
    -0.70
    POSITIVE LOGITS
     NPP
    1.03
    Откры
    0.84
    ttino
    0.83
     Cancell
    0.80
    Planning
    0.79
    Люби
    0.79
    全国
    0.79
    itulo
    0.78
    西瓜
    0.78
    採
    0.76
    Activations Density 0.005%

    No Known Activations