© 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. 10-GEMMASCOPE-RES-131K
    7. 124676
    Prev
    Next
    INDEX
    Explanations

    table_row table_cell

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

    The neuron fires on tokens that contain numerals (e.g. version‐style numbers, IDs, line numbers, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    istische
    -2.22
     \
    -2.14
    
    -1.92
    不愿
    -1.91
     ‘‘
    -1.88
     จาก
    -1.88
    鹟
    -1.85
     kutoka
    -1.84
     —
    -1.84
     trovano
    -1.82
    POSITIVE LOGITS
    .”
    2.69
    of
    2.19
    你会
    2.17
     that
    2.08
     various
    2.03
     esteemed
    2.03
     Kollegen
    2.02
     Organisationen
    2.00
    我国
    2.00
     it
    1.99
    Activations Density 0.042%

    No Known Activations