© 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. 22-GEMMASCOPE-RES-131K
    7. 25232
    Prev
    Next
    INDEX
    Explanations

    java, android, and system imports

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

    The neuron activates strongly on module/package import lines (e.g. “import …” or “package …”) in source code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     after
    -1.40
     on
    -1.30
     while
    -1.28
     at
    -1.20
     when
    -1.20
     so
    -1.20
     Before
    -1.14
     but
    -1.13
     in
    -1.13
     takes
    -1.13
    POSITIVE LOGITS
     créer
    1.12
    毎回
    1.07
     bezw
    1.04
    笞
    1.03
     stylized
    1.03
     contenedores
    1.02
    ulitan
    1.02
     xay
    1.02
     góry
    1.01
     ciem
    1.01
    Activations Density 0.017%

    No Known Activations