© 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. 61293
    Prev
    Next
    INDEX
    Explanations

    receiving data or events

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

    The neuron strongly activates on occurrences of the word “receive” (in any case) within 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
    2
    -2.20
    1
    -2.13
     schlaf
    -2.11
     Begleitung
    -2.05
     一个
    -2.00
    ’
    -1.97
    其他
    -1.96
    .
    -1.91
     Should
    -1.91
     later
    -1.91
    POSITIVE LOGITS
    
    2.38
    賅
    2.30
     chale
    2.20
    屜
    2.17
    
    2.14
    ︕
    2.14
    柃
    2.09
    रीर
    2.09
    ！");
    2.08
    ].
    2.06
    Activations Density 0.014%

    No Known Activations