© 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. 41437
    Prev
    Next
    INDEX
    Explanations

    a/an + noun

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

    The neuron activates on numeric tokens (e.g. numbers, measurements, percentages, or other digit‐based expressions).

    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
     also
    -1.55
     cintur
    -1.54
    𖤍
    -1.51
     également
    -1.43
     тоже
    -1.40
    tieron
    -1.39
    ⅖
    -1.34
     放題
    -1.32
     antigu
    -1.31
    也是
    -1.30
    POSITIVE LOGITS
     other
    2.08
     our
    2.05
    その他の
    1.77
     these
    1.74
     of
    1.72
    他の
    1.66
     your
    1.66
     those
    1.60
     like
    1.58
     by
    1.45
    Activations Density 0.053%

    No Known Activations