© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 84459
    Prev
    Next
    INDEX
    Explanations

    Honda, John, origin, stem, active, Non

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

    This neuron activates on tokens containing digits—that is, it’s detecting numbers (numeric characters) 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_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
     magasiner
    -1.09
    Garantie
    -1.06
     perle
    -1.05
    íš
    -1.04
     kaffe
    -1.03
     saisi
    -1.03
     carbur
    -1.03
     dezelve
    -1.02
     mauva
    -1.02
     菇
    -1.01
    POSITIVE LOGITS
    r
    1.17
    N
    1.10
    n
    1.09
    v
    1.06
    b
    1.06
     main
    1.02
    l
    1.01
    f
    1.01
     R
    0.99
    no
    0.99
    Activations Density 0.006%

    No Known Activations