© 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. 22-GEMMASCOPE-RES-131K
    7. 68382
    Prev
    Next
    INDEX
    Explanations

    as well

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

    This neuron fires on occurrences of the word “as,” especially when used in comparative or “as … as” constructions.

    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
     proprietario
    -1.01
     sophisticated
    -0.93
     अला
    -0.93
     giacca
    -0.90
     does
    -0.87
    قرأ
    -0.86
    ちゃんは
    -0.86
     करता
    -0.85
     Ncert
    -0.84
     would
    -0.84
    POSITIVE LOGITS
     amalgam
    1.13
    zkiem
    1.01
    aarrggbb
    0.99
    RESOURCES
    0.92
    GRect
    0.91
    muş
    0.91
    castic
    0.90
     insinu
    0.90
    ГА
    0.88
     drinken
    0.88
    Activations Density 0.045%

    No Known Activations