© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 98993
    Prev
    Next
    INDEX
    Explanations

    java import statements

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

    The neuron flags occurrences of the “javax” package prefix in import statements (i.e. imports from Java’s standard extension APIs).

    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
     לאחר
    -1.61
     blazing
    -1.59
     proclaiming
    -1.55
     hábito
    -1.54
     myriad
    -1.52
     rampant
    -1.52
     devastated
    -1.50
     überprü
    -1.49
     berücksich
    -1.49
     enraged
    -1.48
    POSITIVE LOGITS
    ⃚
    1.38
    <bos>
    1.35
     mereka
    1.30
     auxquelles
    1.27
    вих
    1.21
    ждении
    1.18
     that
    1.17
    лябин
    1.16
                    
    1.16
    .
    1.16
    Activations Density 0.001%

    No Known Activations