© 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. 57845
    Prev
    Next
    INDEX
    Explanations

    require followed by relative path

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

    The neuron fires on JavaScript “require(…)” calls—i.e. module‐import statements using require.

    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
    
    -0.77
    тельностью
    -0.73
    etro
    -0.70
    idious
    -0.70
     بج
    -0.69
    oida
    -0.65
    一定的
    -0.65
     ƙ
    -0.64
    ダス
    -0.64
     Audubon
    -0.64
    POSITIVE LOGITS
     ./
    3.72
     "./
    3.08
     './
    2.92
    ("./
    2.89
    ./
    2.86
    ('./
    2.80
    ="./
    2.47
    "./
    2.45
     ['./
    2.22
    './
    1.93
    Activations Density 0.157%

    No Known Activations