© 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. 99569
    Prev
    Next
    INDEX
    Explanations

    providing support or valuable information

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

    The neuron fires on occurrences of the verb “provide” (and its inflected stems like provides, providing, provided).

    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
    -4.44
    y
    -4.00
    9
    -3.77
    3
    -3.77
    8
    -3.72
     '
    -3.70
    4
    -3.64
    6
    -3.45
    1
    -3.44
    7
    -3.20
    POSITIVE LOGITS
    瑧
    3.23
    玧
    3.05
    部は
    2.88
    韡
    2.86
    勍
    2.80
     them
    2.72
    霂
    2.67
    
    2.61
    .’
    2.59
    这一刻
    2.59
    Activations Density 0.061%

    No Known Activations