© 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. 22-GEMMASCOPE-RES-131K
    7. 129555
    Prev
    Next
    INDEX
    Explanations

    The neuron flags numeric tokens—especially measurements, percentages, decimals, and other number-like strings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    . after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    웁
    -1.00
     págs
    -0.98
    搅拌
    -0.98
    ﾐ
    -0.96
     resmi
    -0.96
     its
    -0.94
    箭头
    -0.93
    лена
    -0.92
    gı
    -0.91
    ximity
    -0.91
    POSITIVE LOGITS
    section
    1.01
    Kinematic
    0.97
    聞き
    0.94
     determinados
    0.93
    yste
    0.89
     Tourismus
    0.89
     «
    0.88
    create
    0.87
     deliver
    0.87
     leurs
    0.87
    Activations Density 0.126%

    No Known Activations