© 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. 110940
    Prev
    Next
    INDEX
    Explanations

    ranges of values and formats

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

    The neuron fires on the word “range” when it introduces a numerical range or measurement interval.

    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
     in
    -2.28
     and
    -2.13
     have
    -1.84
     still
    -1.80
     will
    -1.76
     method
    -1.73
     then
    -1.73
     went
    -1.71
     take
    -1.64
     now
    -1.60
    POSITIVE LOGITS
     juſ
    2.22
     célè
    1.88
     that
    1.84
    pantalón
    1.82
     infolge
    1.73
     fidé
    1.73
    他想
    1.73
    筇
    1.71
     engend
    1.70
    𐄁
    1.70
    Activations Density 0.274%

    No Known Activations