© 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. 10-GEMMASCOPE-RES-131K
    4. 110856
    Prev
    Next
    INDEX
    Explanations

    lists and conjunctions

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

    The neuron detects items (and the commas around them) in a comma-separated enumeration (i.e. list elements).

    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
     they
    -1.68
     where
    -1.43
     how
    -1.41
     why
    -1.34
    O
    -1.32
     then
    -1.30
    U
    -1.24
    G
    -1.20
    d
    -1.18
     invitamos
    -1.16
    POSITIVE LOGITS
     Speisen
    1.52
    Ᏹ
    1.50
     immagine
    1.43
     to
    1.38
    婳
    1.36
     faldas
    1.31
     compleanno
    1.31
    laşı
    1.30
    ytu
    1.30
    icksburg
    1.30
    Activations Density 0.189%

    No Known Activations