© 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. 34-GEMMASCOPE-RES-131K
    7. 87300
    Prev
    Next
    INDEX
    Explanations

    number followed by period or parenthesis

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

    The neuron detects numerals used as ordered‐list or section markers (e.g. “1.” “2.” “3.” 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_34/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
    więcej
    -1.16
     Terima
    -1.15
    wijze
    -1.14
    久し
    -1.09
    capai
    -1.08
    ＊＊＊
    -1.03
    ＼(^
    -1.03
    📧
    -1.01
     poby
    -1.01
    ómago
    -1.00
    POSITIVE LOGITS
    si
    1.06
    d
    1.00
    a
    0.98
    ni
    0.97
    th
    0.96
    ar
    0.93
    na
    0.91
    la
    0.90
     lastly
    0.90
    で
    0.89
    Activations Density 0.034%

    No Known Activations