© 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. 60670
    Prev
    Next
    INDEX
    Explanations

    Trump fires

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

    The neuron specifically detects the word “commutative,” as in “noncommutative.”

    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
     in
    -0.86
     pensée
    -0.83
     gambling
    -0.77
    せずに
    -0.76
     facilitating
    -0.73
     bite
    -0.73
     still
    -0.72
    بینی
    -0.71
     Française
    -0.69
    Björn
    -0.69
    POSITIVE LOGITS
    itizing
    0.92
     rheinland
    0.89
     plastica
    0.83
     beschrieben
    0.82
     REQUIRE
    0.82
    người
    0.81
    aimeJ
    0.80
    ης
    0.80
     Mille
    0.79
     『
    0.79
    Activations Density 0.003%

    No Known Activations