© 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. 34-GEMMASCOPE-RES-131K
    4. 83198
    Prev
    Next
    INDEX
    Explanations

    motion to or for

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

    The neuron responds to the occurrence of the token “to,” especially when it marks an infinitive or prepositional phrase.

    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
    元々
    -0.94
    Важно
    -0.85
     azioni
    -0.82
     motion
    -0.81
     insuring
    -0.79
     confers
    -0.78
     identificar
    -0.78
     reformas
    -0.77
     conceding
    -0.77
     Antrag
    -0.76
    POSITIVE LOGITS
     reconsider
    0.94
    clar
    0.93
     Clar
    0.91
     Recons
    0.85
    Belle
    0.84
    Entered
    0.84
     inte
    0.82
     entier
    0.81
    vention
    0.80
    join
    0.80
    Activations Density 0.093%

    No Known Activations