© 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. 10-GEMMASCOPE-RES-131K
    4. 85189
    Prev
    Next
    INDEX
    Explanations

    introducing descriptive phrases

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

    The neuron strongly activates on the preposition “with.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     their
    -2.72
     what
    -2.48
     on
    -2.47
     that
    -2.33
     by
    -2.28
     would
    -2.19
     in
    -2.17
     its
    -2.03
     may
    -1.78
     it
    -1.72
    POSITIVE LOGITS
    鶿
    2.05
    Tentang
    1.92
    Aplikasi
    1.91
    Kepala
    1.81
    Penulis
    1.81
    Pemer
    1.75
    Karena
    1.73
    Bahan
    1.70
    Преимущества
    1.70
     divertir
    1.63
    Activations Density 0.063%

    No Known Activations