© 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. 41555
    Prev
    Next
    INDEX
    Explanations

    sequence and novelty

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

    The neuron flags numerical references and ordinals (digits like “2,” “26,” and words like “first,” “second,” “third,” “one”) 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_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
     in
    -3.08
     with
    -2.77
     through
    -2.59
     for
    -2.48
     after
    -2.30
     during
    -2.28
     more
    -2.23
     where
    -2.22
     while
    -2.13
     if
    -2.02
    POSITIVE LOGITS
     évidemment
    1.70
    
    1.68
    扨
    1.67
     oxígeno
    1.66
    カロ
    1.66
    ఽ
    1.59
     gâ
    1.57
     créer
    1.54
     construite
    1.52
    졍
    1.52
    Activations Density 0.209%

    No Known Activations