© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99302
    Prev
    Next
    INDEX
    Explanations

    one of the

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

    The neuron fires most strongly on plural nouns (words ending in “-s”).

    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
     and
    -1.53
    都是
    -1.16
     zowel
    -0.99
     لاع
    -0.99
     alcuni
    -0.97
     الوا
    -0.96
     ストレッチ
    -0.96
    zelfde
    -0.94
     وزار
    -0.93
     проч
    -0.92
    POSITIVE LOGITS
    之一
    1.54
     that
    1.28
     listed
    1.04
     is
    1.03
     in
    1.02
     وهو
    1.02
     pimienta
    0.98
     malheure
    0.98
    guitarra
    0.98
     Situationen
    0.96
    Activations Density 0.070%

    No Known Activations