© 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. 19462
    Prev
    Next
    INDEX
    Explanations

    list separators

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

    The neuron strongly activates on numeric tokens (especially measurements or statistical values, including decimals) 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
    茈
    -1.67
     nieuwe
    -1.58
    ondissement
    -1.55
     rése
    -1.53
    ᠊
    -1.49
     impos
    -1.45
     játé
    -1.41
     redund
    -1.41
    旄
    -1.41
     yeni
    -1.41
    POSITIVE LOGITS
     there
    2.20
     on
    1.96
     from
    1.88
     during
    1.78
     with
    1.74
     each
    1.73
     at
    1.69
     \
    1.69
     until
    1.66
     for
    1.63
    Activations Density 0.047%

    No Known Activations