© 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. 9246
    Prev
    Next
    INDEX
    Explanations

    files and assets

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

    The neuron fires on occurrences of the word “resource” (or its plural “resources”) 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
    𐑂
    -2.45
    速度
    -2.44
    眼睛
    -2.39
     animasi
    -2.36
    ния
    -2.33
    ugeot
    -2.27
    屺
    -2.23
     avantaj
    -2.20
    нг
    -2.19
     Centres
    -2.19
    POSITIVE LOGITS
     \
    3.28
     portugués
    2.77
     is
    2.67
     
    2.48
    
    2.44
     alemán
    2.41
    笋
    2.41
    ⢓
    2.39
     of
    2.36
    <em>
    2.33
    Activations Density 0.014%

    No Known Activations