© 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. 54389
    Prev
    Next
    INDEX
    Explanations

    determiners before concepts or nouns

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

    The neuron fires whenever it sees a numeric token (e.g. years, counts, or other numbers).

    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
     vertrouwen
    -1.69
    konos
    -1.55
     Vereinbarung
    -1.50
     potrebné
    -1.49
     médec
    -1.49
     expérimentés
    -1.49
     décider
    -1.48
     AHEAD
    -1.48
    БА
    -1.48
     délais
    -1.48
    POSITIVE LOGITS
    が
    1.41
    を
    1.35
     very
    1.33
    ;//
    1.25
    %,
    1.24
     检查
    1.23
     from
    1.21
    ).....
    1.20
     only
    1.20
    t
    1.20
    Activations Density 0.012%

    No Known Activations