© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129658
    Prev
    Next
    INDEX
    Explanations

    The neuron is essentially detecting occurrences of the preposition “in.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    in atraumatic restorative treatment

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

    the preposition "in" followed by "the" or other articles, particularly in medical or scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     that
    -1.53
     are
    -1.34
     when
    -1.30
     if
    -1.12
     pomocí
    -1.07
     sometimes
    -1.02
     usually
    -0.97
    有一些
    -0.97
     using
    -0.94
     kanskje
    -0.93
    POSITIVE LOGITS
     Ansprüche
    1.24
    羕
    1.23
     to
    1.15
     komfort
    1.12
    ाहरण
    1.12
    itschrift
    1.09
     clients
    1.09
     우리
    1.09
    嫆
    1.07
    Already
    1.06
    Activations Density 0.190%

    No Known Activations