© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 111138
    Prev
    Next
    INDEX
    Explanations

    src/main/resources directory structure

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

    The neuron fires on filesystem path components (e.g. “src/main/resources” or “src/main/scala”), identifying directory‐style strings with slash separators.

    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
    bius
    -0.83
    ACCIÓN
    -0.82
    istemas
    -0.81
    appelle
    -0.81
    ifikasi
    -0.81
    癥
    -0.77
     rêver
    -0.77
    壢
    -0.76
    nyard
    -0.76
    moke
    -0.76
    POSITIVE LOGITS
    java
    1.58
    resources
    1.13
     java
    1.11
    webapp
    1.09
    scala
    0.82
     python
    0.76
     resources
    0.74
    main
    0.73
    advanced
    0.73
     scot
    0.72
    Activations Density 0.011%

    No Known Activations