© 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. 34-GEMMASCOPE-RES-131K
    4. 581
    Prev
    Next
    INDEX
    Explanations

    list items number

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

    The neuron detects square‐bracket list markers (e.g. the “\[” used in markdown checklist or list item syntax).

    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
     hırka
    -2.36
    饜
    -2.28
    *</
    -2.27
     火鍋
    -2.22
    !';
    -2.22
     calcetines
    -2.20
    삵
    -2.19
     стоковые
    -2.17
    ...»
    -2.16
    …»
    -2.14
    POSITIVE LOGITS
     The
    3.33
     It
    3.31
     In
    3.03
     If
    2.66
     to
    2.64
     There
    2.63
     As
    2.59
     At
    2.50
     Since
    2.44
     there
    2.39
    Activations Density 0.020%

    No Known Activations