© 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. 22-GEMMASCOPE-RES-131K
    7. 27656
    Prev
    Next
    INDEX
    Explanations

    code file imports

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

    The neuron is strongly activated by the names of files or directories in import/require module paths.

    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
    cerely
    -1.13
    >"+
    -1.09
    えっ
    -1.07
    の為
    -1.07
    を行い
    -1.05
    élite
    -1.05
     képes
    -1.05
    な感じ
    -1.05
    に向けて
    -1.05
    んですよね
    -1.05
    POSITIVE LOGITS
    ͊
    1.05
    了好
    1.01
    秘书
    1.01
     perkembangan
    0.95
     виды
    0.94
     urusan
    0.94
    都没
    0.93
     hasta
    0.93
     pembentukan
    0.93
     של
    0.93
    Activations Density 0.008%

    No Known Activations