© 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. 104485
    Prev
    Next
    INDEX
    Explanations

    chapter or number

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

    The neuron selectively fires on numeric tokens (standalone digits or multi‐digit 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
     spurred
    -1.17
     most
    -1.10
     by
    -1.07
     four
    -1.07
     cleverly
    -1.02
     get
    -1.02
     undoubtedly
    -1.01
     even
    -0.99
     so
    -0.99
     other
    -0.99
    POSITIVE LOGITS
     ní
    1.06
    睃
    1.04
    vetor
    1.02
     blí
    1.00
     ){
    0.98
     geladen
    0.97
     rév
    0.97
    enablog
    0.96
     krá
    0.95
     unab
    0.94
    Activations Density 0.028%

    No Known Activations