© 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. 9673
    Prev
    Next
    INDEX
    Explanations

    pairs of words

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

    The main thing this neuron does is detect numeric tokens—years, scores, statistics, and other number-formatted data.

    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
     उदाहरण
    -1.06
     adopts
    -0.93
     Btu
    -0.92
    駅から
    -0.91
     glories
    -0.91
    ־
    -0.90
     ?"
    -0.90
    ϴ
    -0.90
     Messrs
    -0.89
     advices
    -0.89
    POSITIVE LOGITS
     parfüm
    1.15
     tasche
    1.09
     kişilik
    1.06
    sä
    1.04
    relevant
    1.02
     magnifiques
    1.01
    ității
    1.01
    Răsp
    1.00
     pazar
    1.00
     anciennes
    0.99
    Activations Density 0.006%

    No Known Activations