© 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. 2577
    Prev
    Next
    INDEX
    Explanations

    package and import statements

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

    The neuron fires on external‐dependency references in code—things like #include and import/package lines, namespace declarations, file‐extension headers, and domain-style paths.

    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
    newborn
    -1.05
    lindungi
    -1.00
    encouragement
    -0.99
     oração
    -0.97
    penis
    -0.94
    baine
    -0.93
    mika
    -0.93
    Turismo
    -0.93
    tarta
    -0.92
    Anis
    -0.92
    POSITIVE LOGITS
    ´
    1.20
    ia
    1.02
    os
    1.02
    `
    1.02
    ázat
    1.02
    \'
    1.01
    ag
    0.99
     projeto
    0.96
    io
    0.96
     project
    0.96
    Activations Density 0.114%

    No Known Activations