© 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. 3829
    Prev
    Next
    INDEX
    Explanations

    technical specifications and components

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

    The neuron fires on tokens that are names, labels, or other identifiers—i.e. capitalized words (including acronyms and class/field names) and numeric or punctuation-heavy tokens used as headings or structural markers.

    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
     and
    -1.88
     &
    -1.41
    ׇ
    -1.30
     this
    -1.27
     to
    -1.18
     ''
    -1.16
     --
    -1.13
     have
    -1.11
    ِّ
    -1.11
    libatkan
    -1.10
    POSITIVE LOGITS
    ⽽
    1.89
     powerfully
    1.80
     disregarding
    1.78
     captivated
    1.73
     needlessly
    1.70
     defying
    1.70
     ignited
    1.69
     uncovering
    1.66
     puzzling
    1.64
     orchestrated
    1.63
    Activations Density 42.939%

    No Known Activations