© 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. 39725
    Prev
    Next
    INDEX
    Explanations

    page numbers preceded by asterisk

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

    The neuron specializes in detecting the numeric page references (the digits denoting page numbers) within legal case citations.

    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
    子さん
    -1.16
    блок
    -1.09
    сков
    -1.09
    şağı
    -1.07
    gencias
    -1.05
    ॄ
    -1.01
     sés
    -1.00
    НГ
    -0.99
    テイン
    -0.98
    ífero
    -0.98
    POSITIVE LOGITS
     is
    1.09
    χν
    0.94
     where
    0.86
     light
    0.84
     desired
    0.84
    encre
    0.84
    kde
    0.83
     revenir
    0.82
     문제
    0.82
     trattano
    0.81
    Activations Density 0.006%

    No Known Activations