© 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. 15304
    Prev
    Next
    INDEX
    Explanations

    importing and using libraries

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

    This neuron activates on leading indentation whitespace (long runs of space characters at the start of code lines).

    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
     "
    -1.94
    ''
    -1.64
    ,"
    -1.52
     ""
    -1.46
     $^{\
    -1.45
    ".
    -1.41
     ''
    -1.40
    ";
    -1.39
    '"
    -1.37
    ?"
    -1.35
    POSITIVE LOGITS
     aislada
    1.49
     mixta
    1.33
    瑒
    1.29
    Nuorodos
    1.27
     trasera
    1.26
     elástica
    1.24
     принципе
    1.22
    فى
    1.21
     bellissimo
    1.21
     térmica
    1.19
    Activations Density 0.020%

    No Known Activations