© 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. 93394
    Prev
    Next
    INDEX
    Explanations

    squared differences, uncorrelated, months

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

    The neuron is most strongly triggered by numeric characters (digits) appearing in formulas or code, i.e. by numbers.

    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
    aktu
    -1.14
    他
    -1.02
    摩托
    -1.01
     to
    -0.98
    hô
    -0.97
    æa
    -0.93
    érc
    -0.91
    lussen
    -0.91
     entrambi
    -0.90
     sesuai
    -0.90
    POSITIVE LOGITS
     June
    1.05
     all
    1.05
     December
    1.00
     cewek
    0.99
    škas
    0.98
    dalam
    0.97
     pacar
    0.96
     July
    0.96
     September
    0.96
     settembre
    0.95
    Activations Density 0.006%

    No Known Activations