© 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. 25523
    Prev
    Next
    INDEX
    Explanations

    comparisons to null or false

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

    The neuron is triggered by occurrences of the “not-equal” comparison operator ( != ).

    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
    Rüyada
    -1.12
    小行星
    -1.00
    この
    -0.87
     และ
    -0.85
    lampe
    -0.84
    そして
    -0.84
    lization
    -0.82
    ///
    -0.81
    Condol
    -0.81
     два
    -0.80
    POSITIVE LOGITS
    喼
    1.05
    おわりに
    1.04
    ificaciones
    1.02
    protetor
    1.01
    Avantages
    1.00
     probablemente
    0.99
    volkswagen
    0.99
     erinner
    0.98
     çoğu
    0.98
    Ethyl
    0.96
    Activations Density 0.001%

    No Known Activations