© 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. 11407
    Prev
    Next
    INDEX
    Explanations

    providing benefits or function

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

    The neuron activates on occurrences of the verb “provides.”

    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
     there
    -2.17
     it
    -2.05
    because
    -1.87
     these
    -1.86
    2
    -1.85
     as
    -1.76
     in
    -1.73
     by
    -1.71
     while
    -1.67
     at
    -1.65
    POSITIVE LOGITS
    Además
    1.87
     talvez
    1.81
     cremallera
    1.77
     lui
    1.73
     emprego
    1.70
    裥
    1.69
     andere
    1.69
     kinda
    1.67
     seguinte
    1.66
     nobre
    1.65
    Activations Density 0.072%

    No Known Activations