© 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. 10-GEMMASCOPE-RES-131K
    7. 41626
    Prev
    Next
    INDEX
    Explanations

    f<number> or <letter> patterns

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

    The neuron activates strongly on numeric tokens (sequences of digits), i.e. it detects 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_10/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
     pove
    -2.11
    籐
    -1.96
     Vielzahl
    -1.88
    ቭ
    -1.83
    You
    -1.83
    usstsein
    -1.80
     habilidades
    -1.78
    ಿಕ
    -1.77
    alties
    -1.77
     biela
    -1.77
    POSITIVE LOGITS
    ,
    2.14
    </h3>
    2.05
     可以
    1.96
     They
    1.91
     is
    1.70
     übergeben
    1.70
     不是
    1.66
    for
    1.63
    can
    1.63
    也
    1.62
    Activations Density 0.023%

    No Known Activations