© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129080
    Prev
    Next
    INDEX
    Explanations

    The neuron is primarily firing on numeric tokens (i.e. sequences of digits).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    list formatting and code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     in
    -3.05
     on
    -2.45
     this
    -2.41
     as
    -2.41
     more
    -2.33
     that
    -2.31
     utterly
    -2.30
     two
    -2.30
     at
    -2.28
     all
    -2.28
    POSITIVE LOGITS
     ſol
    2.34
     Dinas
    2.28
    genodigd
    2.20
     legendar
    2.17
    ésultats
    2.03
     😁
    2.00
     soooo
    1.99
     exuber
    1.98
     zoude
    1.95
    糁
    1.95
    Activations Density 0.004%

    No Known Activations