© 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. 40061
    Prev
    Next
    INDEX
    Explanations

    command-line tools, code errors, testing libraries

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

    The neuron strongly activates on named software tools or libraries (e.g. “jadx,” “enzyme,” “liquibase,” “aspectj”).

    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
    6
    -3.06
    3
    -2.75
    𓋼
    -2.56
    Despite
    -2.34
    Surprisingly
    -2.27
    8
    -2.20
    7
    -2.19
     agrico
    -2.13
     dibanding
    -2.09
    Although
    -2.05
    POSITIVE LOGITS
    </h3>
    2.94
    </i>
    2.06
    NXG
    1.95
    ቷ
    1.88
     suficiente
    1.83
     '
    1.80
    多大
    1.79
    蹋
    1.77
    ぶつ
    1.75
    ("
    1.74
    Activations Density 0.000%

    No Known Activations