© 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. 21584
    Prev
    Next
    INDEX
    Explanations

    function calls and object creation

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

    The neuron fires on programming API identifiers—class or method names (especially library calls) in source code.

    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
     Each
    -2.06
     Regardless
    -1.98
     Both
    -1.72
     setiap
    -1.67
     ketika
    -1.67
     According
    -1.66
    Each
    -1.66
     '-
    -1.63
     However
    -1.63
     -
    -1.62
    POSITIVE LOGITS
     decoradas
    1.80
    ſtra
    1.78
    じゃないですか
    1.58
     fornire
    1.55
     pintadas
    1.52
    tanaman
    1.51
     ему
    1.50
    踅
    1.50
     estabiliz
    1.50
    ihnachten
    1.47
    Activations Density 0.020%

    No Known Activations