© 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. 34-GEMMASCOPE-RES-131K
    7. 108531
    Prev
    Next
    INDEX
    Explanations

    than meets the eye

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

    The neuron fires on occurrences of “meet” or “meets,” particularly in the phrase “more … meets the eye.”

    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
    協会
    -0.79
    peche
    -0.75
    协
    -0.74
    끽
    -0.74
    ereich
    -0.73
    hesive
    -0.71
    westen
    -0.71
    джин
    -0.71
    میزی
    -0.70
    ByteString
    -0.70
    POSITIVE LOGITS
     meet
    8.13
     meeting
    6.53
     meets
    6.31
    meet
    6.28
    Meet
    6.06
     Meet
    6.03
     met
    5.28
    Meeting
    5.13
    meeting
    5.09
     Meeting
    4.94
    Activations Density 0.318%

    No Known Activations