© 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. 101781
    Prev
    Next
    INDEX
    Explanations

    dates and times

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

    This neuron identifies numeric tokens (multi-digit numbers, decimals, timestamps, etc.) 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
     and
    -1.75
     be
    -1.73
    ṯ
    -1.55
    {}
    -1.45
    impinan
    -1.41
    ながらも
    -1.38
    %</
    -1.37
    ❓
    -1.35
    }$
    -1.34
     名片
    -1.34
    POSITIVE LOGITS
    .
    1.71
    1
    1.71
     entspre
    1.46
    0
    1.45
    仕上げ
    1.45
    不想
    1.41
     szklan
    1.35
    Ⲉ
    1.33
    ?
    1.30
     persön
    1.30
    Activations Density 0.066%

    No Known Activations