© 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. 48444
    Prev
    Next
    INDEX
    Explanations

    proper nouns and punctuation

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

    The neuron is triggered by the “\[” token that opens an optional argument (e.g. the bracket starting the parameter list for a LaTeX environment or command).

    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
    ’
    -2.80
    ↵
    -2.75
     .
    -2.69
    )
    -2.52
     estekak
    -2.45
     has
    -2.44
     just
    -2.41
     still
    -2.39
     first
    -2.36
     impeccable
    -2.36
    POSITIVE LOGITS
    塒
    3.09
     verminder
    3.08
    隳
    2.78
     améli
    2.77
     alent
    2.72
    簓
    2.69
     étend
    2.63
     technisch
    2.61
    糶
    2.58
    }[
    2.56
    Activations Density 0.000%

    No Known Activations