© 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. 22-GEMMASCOPE-RES-131K
    7. 483
    Prev
    Next
    INDEX
    Explanations

    respect to

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

    The neuron activates on instances of the word “respect” as used in the technical phrase “with respect to.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    してました
    -2.17
    StoryboardSegue
    -1.91
    してます
    -1.84
    しちゃ
    -1.77
    ・「
    -1.77
    してた
    -1.66
     desbloquear
    -1.66
    柃
    -1.62
     marcadores
    -1.61
     contratos
    -1.58
    POSITIVE LOGITS
     the
    2.06
     of
    2.03
     یکی
    1.84
    “
    1.81
     \\
    1.70
     to
    1.68
     It
    1.55
    の状態
    1.54
    n
    1.52
     Therefore
    1.47
    Activations Density 0.019%

    No Known Activations