© 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. 103173
    Prev
    Next
    INDEX
    Explanations

    null, none, or undefined followed by punctuation

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

    The neuron spots occurrences of null‐equivalent literal values (e.g. None, null, undefined) 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
     your
    -1.90
    结语
    -1.73
     pourrait
    -1.62
     him
    -1.58
     фотографии
    -1.55
    箆
    -1.55
     esfuerzos
    -1.51
     the
    -1.51
    籙
    -1.51
     sudadera
    -1.50
    POSITIVE LOGITS
    .
    1.97
    What
    1.65
    8
    1.59
    1
    1.58
    שלום
    1.51
    3
    1.48
    ↵↵
    1.47
    𝐈
    1.39
    ्ञ
    1.39
     one
    1.39
    Activations Density 0.012%

    No Known Activations