© 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. 10-GEMMASCOPE-RES-131K
    7. 45070
    Prev
    Next
    INDEX
    Explanations

    Go import statements

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

    The neuron activates on Go import statements (i.e. the “import” keyword that begins an import block).

    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
    ly
    -1.73
     (‘
    -1.66
    us
    -1.63
    ar
    -1.63
    </h1>
    -1.62
    h
    -1.62
    m
    -1.53
    5
    -1.53
    all
    -1.52
    t
    -1.50
    POSITIVE LOGITS
     celui
    1.57
     interessantes
    1.48
    𝐒
    1.45
     wußte
    1.35
    ients
    1.35
     大き
    1.34
     wuß
    1.33
     她
    1.32
    饨
    1.31
     querem
    1.30
    Activations Density 0.008%

    No Known Activations