© 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. 34-GEMMASCOPE-RES-131K
    7. 57095
    Prev
    Next
    INDEX
    Explanations

    questions and code snippets

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

    The neuron fires strongly on terms that appear in generated code import paths and wrapper module names (e.g. “generated,” “Wrapper,” “Gold”) rather than ordinary text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ulisan
    -0.90
     dorado
    -0.88
    хие
    -0.85
     kesi
    -0.85
     konten
    -0.83
     luxem
    -0.82
     Kø
    -0.82
     音
    -0.79
     lignin
    -0.79
    ꉂ
    -0.78
    POSITIVE LOGITS
    writerow
    0.86
    settled
    0.82
    ucha
    0.82
    ettare
    0.82
    fficients
    0.82
     air
    0.81
     лекарства
    0.80
    aried
    0.79
    minlength
    0.78
    ):(
    0.78
    Activations Density 0.000%

    No Known Activations