© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 34894
    Prev
    Next
    INDEX
    Explanations

    comparison operators

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

    The neuron fires on numeric comparisons (especially uses of the literal “0” in relational tests) 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_34/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
     koment
    -1.27
     kontinu
    -1.19
     until
    -1.13
     intelek
    -1.13
     ecosistema
    -1.13
     veremos
    -1.08
     }]
    -1.05
     telefonu
    -1.03
     komer
    -1.03
     })}
    -1.02
    POSITIVE LOGITS
    )
    0.87
    เซ
    0.87
     {
    0.85
     gesch
    0.85
    0
    0.85
     n
    0.82
    quarie
    0.81
     gorge
    0.80
     iniciales
    0.79
    Tuck
    0.79
    Activations Density 0.006%

    No Known Activations