© 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. 48411
    Prev
    Next
    INDEX
    Explanations

    questions and technical terms

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

    This neuron activates on Java source‐file boilerplate elements—especially block‐comment endings (*/) and package/import declarations.

    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
    蒾
    -0.83
     Lindberg
    -0.77
    zels
    -0.74
    рного
    -0.74
    ờ
    -0.72
    erty
    -0.72
     titul
    -0.72
    👁
    -0.71
    sbury
    -0.71
     parfa
    -0.71
    POSITIVE LOGITS
    baomidou
    1.12
    mybatisplus
    1.10
    MetaObject
    0.93
    rensa
    0.91
    kiwa
    0.86
    chains
    0.82
    uary
    0.80
    tionen
    0.79
     fill
    0.79
    줍
    0.79
    Activations Density 0.003%

    No Known Activations