© 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. 9744
    Prev
    Next
    INDEX
    Explanations

    HTML/XML attributes and code prefixes

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

    The neuron fires on numeric tokens, especially decimal and other number literals.

    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
     fanns
    -1.22
     -
    -1.09
     ``
    -1.09
    \#:
    -1.05
     började
    -0.97
     endast
    -0.95
     --
    -0.94
     dicembre
    -0.93
     anvä
    -0.93
     considérable
    -0.91
    POSITIVE LOGITS
     and
    1.10
     aceitar
    1.09
     stronę
    1.05
     trabalha
    1.03
     geprü
    1.02
     beginning
    1.02
    matricula
    1.02
     וכל
    1.00
    Prijs
    1.00
     clínicos
    0.99
    Activations Density 0.023%

    No Known Activations