© 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. 23621
    Prev
    Next
    INDEX
    Explanations

    more or less than

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

    The neuron strongly activates on the word “more,” i.e. it detects occurrences of that comparative adverb.

    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
     or
    -1.59
     bepaald
    -1.36
     slightly
    -1.24
     gekomen
    -1.23
     bepaalde
    -1.20
     atentos
    -1.16
     geométrico
    -1.14
    を行い
    -1.14
     experimentado
    -1.13
    をします
    -1.13
    POSITIVE LOGITS
     than
    1.91
     in
    1.27
     then
    1.21
     besides
    1.17
    ebly
    1.08
     Then
    1.02
    ukary
    0.99
     compared
    0.99
     addition
    0.98
    𝜇
    0.98
    Activations Density 0.029%

    No Known Activations