© 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. 103336
    Prev
    Next
    INDEX
    Explanations

    quotations and punctuation

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

    The neuron fires on numeric character‐entity codes (the digits in HTML/XML entities like ", >, ', 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
     several
    -1.12
     enormous
    -1.11
    !!!!!
    -1.10
     increasing
    -1.09
     from
    -1.09
     what
    -1.08
    ！　
    -1.08
     when
    -1.08
     bringing
    -1.07
     steadily
    -1.07
    POSITIVE LOGITS
    ;
    1.80
    ;(
    1.17
     oer
    1.13
     wondrous
    1.11
     immen
    1.08
     ™
    1.05
     debacle
    1.05
     appa
    1.05
    ,;
    1.04
    羿
    1.03
    Activations Density 0.010%

    No Known Activations