© 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. 34-GEMMASCOPE-RES-131K
    7. 58652
    Prev
    Next
    INDEX
    Explanations

    java, apache, androidx imports

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

    The neuron activates on tokens that are parts of code identifiers and qualified names (e.g. namespace, package, import, or domain labels).

    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
     not
    -1.21
     firstly
    -1.13
     neither
    -1.02
     what
    -1.00
     all
    -1.00
     both
    -0.98
     our
    -0.97
    大家的
    -0.96
     equated
    -0.94
    ついで
    -0.92
    POSITIVE LOGITS
     harrowing
    1.07
    os
    1.01
    ative
    1.01
    美味
    0.99
    letzt
    0.98
     discouraging
    0.96
     tumultuous
    0.96
     ""){
    0.95
    oo
    0.94
    laubt
    0.93
    Activations Density 0.038%

    No Known Activations