© 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. 34-GEMMASCOPE-RES-131K
    7. 60213
    Prev
    Next
    INDEX
    Explanations

    in contact or touch

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

    The neuron primarily activates on the preposition “in,” especially when it appears in phrases like “in touch,” “in contact,” or “into.”

    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
    orescence
    -0.79
    КУ
    -0.78
     Confused
    -0.76
     Invited
    -0.75
    üsü
    -0.74
    ässä
    -0.73
    htiö
    -0.73
    Turismo
    -0.72
     deler
    -0.70
    箐
    -0.70
    POSITIVE LOGITS
     contact
    6.66
    contact
    5.19
    Contact
    4.81
     Contact
    4.59
     contacto
    4.38
    CONTACT
    3.86
     CONTACT
    3.84
     contato
    3.83
     kontakt
    3.61
     контакт
    3.59
    Activations Density 0.079%

    No Known Activations