© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 45037
    Prev
    Next
    INDEX
    Explanations

    closing quotes or parentheses followed by as

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

    This neuron fires on Python file‐opening calls (instances of the `open(…)` function, especially in `with open(...)`).

    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
     then
    -1.68
     not
    -1.45
     poniendo
    -1.41
     setContent
    -1.39
    </td>
    -1.34
    </h2>
    -1.27
     But
    -1.25
    deri
    -1.24
     llevando
    -1.24
    escence
    -1.23
    POSITIVE LOGITS
    嗵
    1.42
    lampen
    1.41
    Евгений
    1.41
    ,
    1.38
     zdan
    1.38
    Mohamed
    1.37
    ﹝
    1.35
    Алексей
    1.34
     soucis
    1.33
    האם
    1.32
    Activations Density 0.003%

    No Known Activations