© 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. 131031
    Prev
    Next
    INDEX
    Explanations

    The neuron is picking out numeric tokens (e.g. years, quantities, or other digit sequences).

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

    and, or, plus, other connectors

    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
     parámetros
    -1.37
    
    -1.28
    埽
    -1.26
     westfalen
    -1.23
    菒
    -1.19
    컹
    -1.16
     raiſ
    -1.15
     colonnes
    -1.15
     egenskaper
    -1.15
     parlement
    -1.13
    POSITIVE LOGITS
     and
    3.08
    以及
    1.55
     oraz
    1.41
     valamint
    1.38
     plus
    1.38
     Additionally
    1.34
     as
    1.34
     sowie
    1.30
     along
    1.27
     además
    1.24
    Activations Density 0.153%

    No Known Activations