© 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. 131033
    Prev
    Next
    INDEX
    Explanations

    foreign words

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

    The neuron activates on numeric tokens—particularly standalone numbers and numeric values (including decimals) in the text.

    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
    m
    -2.06
    h
    -1.94
    o
    -1.65
    ep
    -1.49
     werking
    -1.47
    r
    -1.40
     ravi
    -1.38
     naturlig
    -1.36
     yogur
    -1.34
     accidente
    -1.33
    POSITIVE LOGITS
     the
    1.59
     by
    1.58
    xxi
    1.57
     same
    1.54
     new
    1.51
    ’
    1.48
     такой
    1.48
    钤
    1.47
     bezogen
    1.47
     well
    1.47
    Activations Density 0.002%

    No Known Activations