© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100532
    Prev
    Next
    INDEX
    Explanations

    engine cylinder configurations

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

    The neuron is highly sensitive to numeric measurements (especially decimals) in technical or specification contexts.

    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
    能够
    -1.38
     برای
    -1.35
    相同
    -1.34
    ↵↵↵
    -1.31
    他的
    -1.30
    makeat
    -1.29
    已經
    -1.27
    謦
    -1.27
    ,”
    -1.27
    攆
    -1.27
    POSITIVE LOGITS
    穡
    1.43
    💲
    1.41
     ONLY
    1.38
    霎
    1.37
    的头
    1.36
     saque
    1.36
     then
    1.32
    霑
    1.28
     добре
    1.26
     with
    1.25
    Activations Density 0.013%

    No Known Activations