© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42251
    Prev
    Next
    INDEX
    Explanations

    use and limitations

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

    The neuron strongly activates on the token “use” (including in XML tags like `<use>` or as the standalone keyword in code and comments).

    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
     the
    -1.80
     they
    -1.43
    )}+
    -1.26
    ’
    -1.19
    rías
    -1.19
     a
    -1.16
    bearded
    -1.16
     möjlighet
    -1.13
     
    -1.13
     ‘
    -1.10
    POSITIVE LOGITS
    8
    1.66
    期限
    1.35
     Use
    1.34
     شهرد
    1.34
    一定会
    1.34
    個月
    1.31
     Giappone
    1.28
     Uses
    1.27
    CHOOL
    1.26
    ໆ
    1.26
    Activations Density 0.210%

    No Known Activations