© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 93092
    Prev
    Next
    INDEX
    Explanations

    Canton, List

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

    The neuron activates strongly on numeric tokens—digits or numbers—wherever they appear in the document.

    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
     anderen
    -1.03
    が無い
    -1.02
     to
    -1.02
    に戻る
    -1.00
    向けの
    -0.96
     untuk
    -0.95
    _'.$
    -0.93
    เพื่อ
    -0.93
    されていない
    -0.93
    に見える
    -0.91
    POSITIVE LOGITS
    认真的
    1.02
     Abor
    0.97
    褰
    0.95
    ТВ
    0.93
    ұл
    0.93
    Cry
    0.92
    odyne
    0.92
    וה
    0.92
     indisputable
    0.91
     väh
    0.90
    Activations Density 0.001%

    No Known Activations