© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43738
    Prev
    Next
    INDEX
    Explanations

    URLs and surrounding text

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

    The neuron is specialized to spot numeric tokens—especially inline numbers, decimals, and hyphenated numerical values in 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
     "",
    -1.73
     лишь
    -1.61
     périodes
    -1.47
     aforementioned
    -1.46
    那個
    -1.43
     “...
    -1.43
     "-
    -1.41
     "--
    -1.41
    に対し
    -1.41
     "/
    -1.38
    POSITIVE LOGITS
    .
    1.63
     they
    1.59
    _
    1.50
    螃
    1.45
     as
    1.42
    another
    1.38
     \
    1.37
    autre
    1.34
     {
    1.31
    吅
    1.31
    Activations Density 0.073%

    No Known Activations