© 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. 22-GEMMASCOPE-RES-131K
    7. 69130
    Prev
    Next
    INDEX
    Explanations

    numbers and citations

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

    The neuron strongly activates on numeric tokens—especially multi‐digit Arabic numerals used for list or section numbering.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    рии
    -0.96
    Forex
    -0.95
    ++$
    -0.93
    [{{
    -0.91
     peculiarity
    -0.89
    }{%
    -0.88
    velu
    -0.88
     entonces
    -0.88
     Zé
    -0.88
    FLA
    -0.87
    POSITIVE LOGITS
    bis
    0.86
    δ
    0.84
     ות
    0.82
    uniform
    0.82
     prompt
    0.82
     Dont
    0.81
    inst
    0.81
     suministros
    0.80
     erlaubt
    0.80
    backed
    0.80
    Activations Density 0.002%

    No Known Activations