© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77140
    Prev
    Next
    INDEX
    Explanations

    intellij, jetbrains, project imports

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

    The neuron activates on the individual components of fully-qualified package/import namespace paths (e.g. the “com”, “intellij”, “openapi”, etc. in Java import or package declarations).

    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
    ávajú
    -0.80
    スピ
    -0.73
     tengan
    -0.71
    uchi
    -0.70
    vore
    -0.70
    avro
    -0.70
    維持
    -0.69
     elimin
    -0.69
    敷地
    -0.69
    wiet
    -0.68
    POSITIVE LOGITS
     my
    1.30
     project
    1.10
     virtual
    0.88
    virtual
    0.80
    project
    0.79
    Project
    0.78
     Virtual
    0.77
    소
    0.72
    DataManager
    0.72
    ishness
    0.69
    Activations Density 0.009%

    No Known Activations