© 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. 80992
    Prev
    Next
    INDEX
    Explanations

    yourself

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

    This neuron detects direct second-person address constructions, especially the pronoun “you” and its associated verbs.

    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
     بتوان
    -2.05
     ihres
    -1.91
     ihrer
    -1.77
     ihrem
    -1.72
     خودش
    -1.70
     ihren
    -1.61
     their
    -1.55
     themselves
    -1.54
    其
    -1.44
     its
    -1.42
    POSITIVE LOGITS
     yourself
    5.56
     your
    5.41
    yourself
    3.53
     yourselves
    3.00
     Yourself
    2.84
    Your
    2.64
     YOURSELF
    2.47
    your
    2.39
    你自己
    2.23
    ของคุณ
    2.13
    Activations Density 0.148%

    No Known Activations