© 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. 47510
    Prev
    Next
    INDEX
    Explanations

    provide a service or thing

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

    The neuron detects uses of the verb “provide” (including its inflected forms) 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
     dwóch
    -2.08
    3
    -1.87
    掲
    -1.80
    extremely
    -1.76
    1
    -1.70
    䛗
    -1.70
     limitaciones
    -1.69
     нескольких
    -1.66
    9
    -1.64
     médaille
    -1.63
    POSITIVE LOGITS
     Initially
    1.79
     Additionally
    1.78
     Sadly
    1.69
     Ultimately
    1.63
     Evidently
    1.56
     Aside
    1.55
     Typically
    1.55
     Originally
    1.53
     Despite
    1.51
     Apparently
    1.51
    Activations Density 0.069%

    No Known Activations