© 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. 73060
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

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

    This neuron fires on table‐layout and cell‐formatting markup (e.g. HTML `<th>` tags, colspan/align attributes, and wiki-table cell lines).

    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
     réduire
    -1.47
     You
    -1.46
     той
    -1.29
     اهداف
    -1.27
    athered
    -1.23
     fyra
    -1.23
     !!!!!
    -1.22
     nettoyer
    -1.22
     —
    -1.20
     confines
    -1.20
    POSITIVE LOGITS
     because
    2.06
    Since
    1.77
     after
    1.76
    After
    1.75
     since
    1.70
     for
    1.65
     häufig
    1.63
     Aéroport
    1.58
    Because
    1.48
     this
    1.46
    Activations Density 0.001%

    No Known Activations