© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 101358
    Prev
    Next
    INDEX
    Explanations

    date ranges and times

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

    The neuron fires on numeric tokens—years, dates, percentages, and other 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
     two
    -1.47
     first
    -1.47
     a
    -1.47
     cuando
    -1.36
     because
    -1.35
     but
    -1.30
     terakhir
    -1.30
     four
    -1.27
    🌸
    -1.26
    👀
    -1.23
    POSITIVE LOGITS
     of
    1.48
    نامج
    1.38
     goû
    1.20
    咿
    1.19
    𝓲
    1.19
    咳咳
    1.18
    vegli
    1.18
     there
    1.17
    わけです
    1.16
    Inhalts
    1.16
    Activations Density 0.081%

    No Known Activations