© 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. 34-GEMMASCOPE-RES-131K
    7. 86824
    Prev
    Next
    INDEX
    Explanations

    equality and comparison

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

    The neuron fires on programming‐language tokens (identifiers, numeric literals, operators, file‐path fragments, etc.) rather than ordinary prose words.

    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
     hijo
    -0.82
     mão
    -0.77
     يناير
    -0.76
    minton
    -0.73
    xbb
    -0.72
    rinhos
    -0.71
    Empirical
    -0.67
    contributors
    -0.67
     鮮
    -0.67
    нор
    -0.66
    POSITIVE LOGITS
     equality
    3.30
     Equality
    2.66
    Equality
    2.52
    equality
    2.47
     equal
    2.30
     comparison
    2.23
     comparing
    2.17
     Equal
    2.16
     Equals
    2.09
     equals
    2.06
    Activations Density 0.114%

    No Known Activations