© 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. 22-GEMMASCOPE-RES-131K
    7. 16013
    Prev
    Next
    INDEX
    Explanations

    Q: Thanks For Vehicles

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

    This neuron detects occurrences of the literal token “null” (i.e. null checks) in code snippets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     its
    -1.14
     mobilya
    -0.93
    だったので
    -0.92
    Bref
    -0.91
    instead
    -0.90
     warned
    -0.88
    ēja
    -0.87
    眦
    -0.87
     solução
    -0.85
     CALIFOR
    -0.84
    POSITIVE LOGITS
    iotensin
    0.89
     Iš
    0.86
    дру
    0.83
    Un
    0.83
    вости
    0.82
     Еще
    0.81
    rados
    0.81
    ⇩
    0.80
    ्त
    0.79
    ùn
    0.79
    Activations Density 0.000%

    No Known Activations