© 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. 22-GEMMASCOPE-RES-131K
    7. 39534
    Prev
    Next
    INDEX
    Explanations

    numbers and ranges

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

    The neuron is triggered by numeric tokens—numbers, percentages, ranges, and measurement 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_22/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
    مدیر
    -1.13
    بدون
    -1.09
    Penulis
    -1.08
    álise
    -1.08
    莢
    -1.05
    drei
    -1.05
    celotti
    -1.03
     diterapkan
    -1.03
    руктура
    -1.03
     beijo
    -1.03
    POSITIVE LOGITS
     finalmente
    1.09
    toHaveBeen
    1.06
    tml
    1.06
     or
    1.04
    preferably
    1.03
     sonunda
    1.03
     preferably
    0.99
     funcionales
    0.95
    TM
    0.92
     US
    0.91
    Activations Density 0.015%

    No Known Activations