© 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. 15116
    Prev
    Next
    INDEX
    Explanations

    UI automation and testing

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

    The neuron is triggered by programming or API identifiers and keywords—i.e. code tokens like method names, class names, and function calls.

    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
     and
    -1.38
     هنا
    -1.16
    在这里
    -1.16
     here
    -1.14
     aici
    -1.12
     tungkol
    -1.10
     اینجا
    -1.09
     فقط
    -1.09
     использования
    -1.02
     попы
    -1.02
    POSITIVE LOGITS
     during
    1.20
     on
    1.04
    chọn
    1.03
    ଵ
    1.03
     any
    1.02
    gning
    1.02
     altering
    1.01
    なくなる
    0.99
    <h2>
    0.99
     one
    0.98
    Activations Density 0.153%

    No Known Activations