© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129939
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on numeric tokens (i.e. sequences of digits).

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

    numerical or boolean sequences

    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
     ribuan
    -1.16
    tayl
    -1.03
    Exceeded
    -1.02
     ratusan
    -1.00
     inš
    -0.98
    Recherche
    -0.97
    empêcher
    -0.96
    ナメント
    -0.96
     akhirnya
    -0.96
     biasanya
    -0.95
    POSITIVE LOGITS
     Hatfield
    0.90
       
    0.89
    cuito
    0.87
    angliski
    0.85
     kna
    0.85
    ڕ
    0.85
     POT
    0.85
     U
    0.83
     EZ
    0.82
    걍
    0.82
    Activations Density 0.005%

    No Known Activations