© 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. 10-GEMMASCOPE-RES-131K
    7. 8854
    Prev
    Next
    INDEX
    Explanations

    java.util

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

    The neuron detects import lines referencing Java’s “java.util” package.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     krep
    -2.20
    鬭
    -2.16
    阆
    -2.14
    fch
    -2.13
     veículos
    -2.08
    AXB
    -2.08
     conocidas
    -2.06
    贗
    -2.05
    纮
    -2.05
    XIC
    -2.03
    POSITIVE LOGITS
    6
    4.28
    4
    4.28
    7
    4.13
    1
    4.09
    0
    3.95
    5
    3.95
    3
    3.88
    8
    3.61
    9
    3.42
    2
    3.41
    Activations Density 0.010%

    No Known Activations