© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 129665
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly fires on the fragment “ared” as in the word “adhered,” i.e. it spots the license‐style phrase “the following conditions are adhered to.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    as long as

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     الذي
    -1.55
     dergleichen
    -1.54
     the
    -1.46
    -1.38
     "/
    -1.36
     longterm
    -1.34
     igång
    -1.34
     beantragt
    -1.32
     waren
    -1.27
     "{\"
    -1.27
    POSITIVE LOGITS
     in
    1.94
     by
    1.68
     while
    1.52
    crochet
    1.52
     when
    1.50
     during
    1.49
     throughout
    1.45
    jewelry
    1.41
    bracelet
    1.41
    antique
    1.39
    Activations Density 0.041%

    No Known Activations