© 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. 90606
    Prev
    Next
    INDEX
    Explanations

    verbs after "to"

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

    The neuron specifically detects the infinitive marker “to” when it introduces a verb (the “to-” of an infinitive).

    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
     and
    -1.84
     SDLK
    -1.81
     maart
    -1.79
     this
    -1.77
     "..\..\
    -1.76
    hiva
    -1.76
    vous
    -1.74
    that
    -1.73
     all
    -1.66
     که
    -1.64
    POSITIVE LOGITS
     dando
    2.00
     insanely
    1.88
     evitando
    1.83
     entrando
    1.81
     
    1.80
     usando
    1.79
     sichere
    1.77
    分かります
    1.73
    に関して
    1.73
     ridiculously
    1.73
    Activations Density 0.074%

    No Known Activations