© 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. 10-GEMMASCOPE-RES-131K
    7. 59788
    Prev
    Next
    INDEX
    Explanations

    to + verb

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

    The neuron strongly fires on the standalone token “to” (the infinitive‐ or preposition “to”).

    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
    </b>
    -2.05
    を書く
    -2.02
    靫
    -1.98
    باره
    -1.80
    鱨
    -1.79
     voda
    -1.77
     preocupado
    -1.75
     tvo
    -1.75
     unido
    -1.73
    masyarakat
    -1.73
    POSITIVE LOGITS
    The
    2.23
    7
    2.17
    6
    2.05
    )
    2.03
    5
    2.03
    ."
    2.02
    8
    1.99
    ot
    1.97
    ',
    1.92
     anderem
    1.88
    Activations Density 0.003%

    No Known Activations