© 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. 4332
    Prev
    Next
    INDEX
    Explanations

    java spring imports

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

    The neuron fires on code‐punctuation tokens—particularly semicolons and opening braces in Java source.

    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
     other
    -0.91
    farol
    -0.89
     Incluso
    -0.88
     Allí
    -0.88
     within
    -0.85
     in
    -0.84
     endwhile
    -0.84
     larger
    -0.83
    шее
    -0.82
    ayant
    -0.82
    POSITIVE LOGITS
     spring
    1.08
    Spring
    1.03
    Long
    0.99
    actu
    0.99
    Optional
    0.98
    ports
    0.96
    pring
    0.94
     Spring
    0.92
    spring
    0.91
    ArgsConstructor
    0.91
    Activations Density 0.005%

    No Known Activations