© 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. 10-GEMMASCOPE-RES-131K
    7. 101335
    Prev
    Next
    INDEX
    Explanations

    connection with

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

    The neuron detects occurrences of the word “connection,” especially in the phrase “in connection with.”

    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
    '
    -2.27
    ᴘ
    -1.73
     same
    -1.70
    {
    -1.69
    </h1>
    -1.67
     tất
    -1.64
    所有的
    -1.59
     there
    -1.57
    之心
    -1.52
    )
    -1.52
    POSITIVE LOGITS
     our
    2.28
    </em>
    2.05
     But
    1.76
    袿
    1.74
    uterte
    1.70
    rosophila
    1.65
    YNAMICS
    1.64
    remia
    1.62
    ropshire
    1.59
    sibilidad
    1.57
    Activations Density 0.017%

    No Known Activations