© 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. 69138
    Prev
    Next
    INDEX
    Explanations

    whatever you

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

    The neuron fires on occurrences of the second-person pronouns “you” and “your,” marking direct address to the reader.

    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
     أيام
    -1.09
    Ḏ
    -0.93
    attori
    -0.90
     چنین
    -0.89
    lijden
    -0.87
     poszczegól
    -0.87
    ülerin
    -0.86
    golang
    -0.84
     ημέ
    -0.84
    SPP
    -0.83
    POSITIVE LOGITS
     whatever
    1.97
    Whatever
    1.57
    無論
    1.41
     your
    1.37
     Whatever
    1.32
     likely
    1.29
     probablemente
    1.27
     you
    1.23
    whatever
    1.21
    どんな
    1.16
    Activations Density 0.041%

    No Known Activations