© 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. 31470
    Prev
    Next
    INDEX
    Explanations

    spring framework

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

    The neuron selectively activates on Java code identifiers and keywords (e.g. import, package, class names, method names) rather than on ordinary English text.

    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
     hummus
    -0.79
     Ducati
    -0.79
     cupcakes
    -0.78
     sätta
    -0.77
     cupcake
    -0.77
     XY
    -0.77
     DONE
    -0.77
    ugio
    -0.77
     Sindh
    -0.77
     Gorilla
    -0.76
    POSITIVE LOGITS
     spring
    1.11
     Wisconsin
    1.03
    springframework
    0.99
     SPRING
    0.93
    assertj
    0.91
     Spring
    0.91
     Springs
    0.89
     reactor
    0.87
    rature
    0.85
    Spring
    0.84
    Activations Density 0.087%

    No Known Activations