© 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. 84194
    Prev
    Next
    INDEX
    Explanations

    class definitions

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

    The neuron activates on standalone numeric tokens (including integers and decimals) in code or 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
     ornamentation
    -0.98
     spesifik
    -0.98
     Pes
    -0.90
    TEK
    -0.88
     Zusätzlich
    -0.88
     leksikon
    -0.86
     داشتند
    -0.85
     futur
    -0.85
    breviations
    -0.85
    дут
    -0.84
    POSITIVE LOGITS
     Menschheit
    0.96
     a
    0.90
     some
    0.88
     Geistes
    0.86
    dellín
    0.85
    ()],
    0.85
     bürger
    0.84
     gemeinsam
    0.83
    ↵↵↵↵↵↵
    0.83
     equality
    0.82
    Activations Density 0.014%

    No Known Activations