© 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. 22226
    Prev
    Next
    INDEX
    Explanations

    gas turbine engines

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

    The neuron is tuned to detect occurrences of “turbine” (and its sub-tokens) in technical descriptions.

    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
    “
    -3.03
     :/
    -2.91
    ，“
    -2.84
     unſ
    -2.72
    ：“
    -2.69
    凊
    -2.69
    7
    -2.56
    ’
    -2.55
    :“
    -2.52
    袮
    -2.48
    POSITIVE LOGITS
    鹬
    2.38
    戇
    2.30
    考える
    2.19
    刧
    2.19
     весна
    2.13
    あえず
    2.11
    abab
    2.09
    ABLO
    2.09
    baca
    2.09
                    
    2.09
    Activations Density 0.006%

    No Known Activations