© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13739
    Prev
    Next
    INDEX
    Explanations

    error, accident, price, dependence

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

    The neuron fires on numeric expressions—digits and numbers (including counts, measurements, percentages, etc.).

    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
    primarily
    -1.45
    generally
    -1.45
    basically
    -1.41
    mainly
    -1.40
    essentially
    -1.38
     meub
    -1.37
     maniere
    -1.36
    voyer
    -1.32
     predominantly
    -1.29
    trying
    -1.27
    POSITIVE LOGITS
     its
    2.44
     by
    2.22
     before
    1.66
     after
    1.58
     when
    1.45
     with
    1.40
     without
    1.39
     because
    1.39
     although
    1.35
     through
    1.29
    Activations Density 0.464%

    No Known Activations