© 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. 25870
    Prev
    Next
    INDEX
    Explanations

    code delimiters and conditionals

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

    The neuron activates on numeric tokens (digits or numbers) 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
     honneur
    -1.16
    킁
    -1.16
     frequentemente
    -1.16
     gründ
    -1.13
     roupas
    -1.11
    
    -1.11
     rythme
    -1.07
     maa
    -1.07
     rembour
    -1.07
     vœ
    -1.06
    POSITIVE LOGITS
     if
    1.66
     or
    1.55
     just
    1.27
     либо
    1.22
     on
    1.20
     despite
    1.17
     regardless
    1.13
     either
    1.11
     seemingly
    1.11
     need
    1.10
    Activations Density 0.001%

    No Known Activations