© 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. 10-GEMMASCOPE-RES-131K
    7. 60415
    Prev
    Next
    INDEX
    Explanations

    DOM manipulation and assignments

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

    The neuron detects numeric literals with decimal points (floating‐point numbers) in 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
     to
    -1.93
     such
    -1.75
     :
    -1.52
     justamente
    -1.51
     from
    -1.50
     “
    -1.43
    </u>
    -1.41
    </h4>
    -1.38
    珍惜
    -1.36
     involving
    -1.32
    POSITIVE LOGITS
    
    1.89
     bolsillos
    1.68
     reciclaje
    1.66
     tránsito
    1.60
     barcos
    1.52
     была
    1.51
     bluza
    1.49
     школу
    1.45
     dekoratif
    1.45
    рия
    1.45
    Activations Density 0.014%

    No Known Activations