© 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. 102881
    Prev
    Next
    INDEX
    Explanations

    Vert, Virginia VT, Subscribes, Error, AS IS

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

    The neuron is detecting Java package and import declarations (the “package”/“import” keywords and their accompanying punctuation).

    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
    棧
    -0.84
    통
    -0.83
    django
    -0.81
    conian
    -0.78
    SEGUIR
    -0.75
    Conta
    -0.73
    Voting
    -0.73
    Visiting
    -0.72
    ńskich
    -0.72
     MSF
    -0.71
    POSITIVE LOGITS
     Vert
    0.99
     JsonObject
    0.96
     Virginia
    0.94
    vertx
    0.91
     virginia
    0.85
     codecs
    0.85
    Vert
    0.85
     Güter
    0.82
     monta
    0.81
     schlä
    0.81
    Activations Density 0.015%

    No Known Activations