© 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. 22-GEMMASCOPE-RES-131K
    7. 14021
    Prev
    Next
    INDEX
    Explanations

    equality and comparison checks

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

    This neuron detects tokens related to equality comparisons (e.g. method names “Equals,” the “==” operator, and equality‐trait names).

    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
     возле
    -1.14
     menjelaskan
    -1.13
    PMailer
    -1.11
    ˂
    -1.09
     asociación
    -1.09
     significativos
    -1.08
    
    -1.07
    
    -1.05
     客户
    -1.05
     BELIEVE
    -1.05
    POSITIVE LOGITS
     other
    2.06
     this
    1.65
     when
    1.62
     and
    1.38
     with
    1.36
     because
    1.33
     two
    1.29
     undeniably
    1.28
     if
    1.28
     any
    1.27
    Activations Density 0.002%

    No Known Activations