© 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. 22-GEMMASCOPE-RES-131K
    4. 154
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions

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

    The neuron flags uncommon, content-bearing words (especially longer, multisyllabic nouns and adjectives) rather than common function 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_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
    heiros
    -0.85
    iffen
    -0.82
     not
    -0.81
    ╞
    -0.79
     fof
    -0.79
    —"
    -0.77
    つき
    -0.77
    Возраст
    -0.76
    Например
    -0.76
     årene
    -0.75
    POSITIVE LOGITS
     but
    5.03
     nhưng
    2.70
     But
    2.63
     แต่
    2.47
    But
    2.38
     लेकिन
    2.30
    但
    2.23
    but
    2.22
    但是
    2.17
     ولی
    2.17
    Activations Density 0.055%

    No Known Activations