© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 75299
    Prev
    Next
    INDEX
    Explanations

    checking availability or emptiness

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

    This neuron activates on tokens that express negation or absence checks in code (e.g. “not,” “empty,” “available,” “Contained,” “In,” “Row”).

    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
    常
    -0.89
    ៅ
    -0.85
    ỡng
    -0.85
    nodes
    -0.84
    研究所
    -0.80
     of
    -0.80
     Such
    -0.79
     for
    -0.79
    衙
    -0.79
     Για
    -0.79
    POSITIVE LOGITS
    写入
    0.93
    Eure
    0.85
    只剩
    0.84
    Mamma
    0.82
    限り
    0.82
    єї
    0.82
    Chili
    0.82
    savevideo
    0.81
    新しく
    0.80
    Beb
    0.79
    Activations Density 0.010%

    No Known Activations