© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69632
    Prev
    Next
    INDEX
    Explanations

    fetch and retrieve

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

    The neuron fires on occurrences of the word “fetch” (in any form or case) used to refer to retrieving or fetching data.

    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
     aprendido
    -2.86
    ❓
    -2.63
    鹇
    -2.61
    
    -2.55
    玏
    -2.55
     appartement
    -2.52
     approche
    -2.48
    𓐍
    -2.45
    itself
    -2.42
     作り方
    -2.42
    POSITIVE LOGITS
     ‘’
    2.64
     
    2.48
    <bos>
    2.44
    1
    2.42
     enmar
    2.28
    さに
    2.25
    pX
    2.23
     Там
    2.23
     yaklaşık
    2.22
     fetching
    2.20
    Activations Density 0.010%

    No Known Activations