© 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. 69500
    Prev
    Next
    INDEX
    Explanations

    all preceding a noun category

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

    The neuron activates on occurrences of the quantifier “all.”

    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
    ⟣
    -2.44
     largely
    -1.95
     très
    -1.75
    出来的
    -1.75
    ◔
    -1.73
    是因为
    -1.70
    mainly
    -1.70
    mostly
    -1.70
     exceedingly
    -1.68
     Dinas
    -1.66
    POSITIVE LOGITS
     our
    2.36
     from
    2.13
     of
    2.09
     -
    1.90
     with
    1.81
     reinforces
    1.80
    瑧
    1.77
     provides
    1.76
    Médaille
    1.71
     brings
    1.70
    Activations Density 0.066%

    No Known Activations