© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 89757
    Prev
    Next
    INDEX
    Explanations

    sitting and settling

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

    The neuron is selectively detecting first‐person self‐references (e.g. “I,” “my”) along with the author’s personal actions and narrative voice.

    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
     sartén
    -0.91
    を実行
    -0.91
    held
    -0.81
    arta
    -0.78
     held
    -0.77
    alucía
    -0.77
    GroupLayout
    -0.76
    db
    -0.76
    pens
    -0.75
    ora
    -0.75
    POSITIVE LOGITS
     plo
    1.17
     settle
    1.15
     sit
    1.15
    坐下
    1.14
    Sit
    1.13
     seating
    1.07
     seat
    1.02
     settles
    1.00
    sit
    0.98
     seated
    0.98
    Activations Density 0.011%

    No Known Activations