© 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-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 432
    Prev
    Next
    INDEX
    Explanations

    This neuron fires strongly on occurrences of the pronouns “we” and “you,” marking direct first‐ and second‐person address.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    0.26
    ().
    0.26
    :
    0.25
    ."
    0.25
    ".
    0.24
     .
    0.24
     itself
    0.23
    .[
    0.23
    ]
    0.23
              
    0.23
    POSITIVE LOGITS
     Trebuie
    0.33
     Análisis
    0.30
    ighed
    0.29
    ಿದ್ದೇವೆ
    0.29
    गरानी
    0.29
    isure
    0.28
    apons
    0.28
     Chứng
    0.28
    都知道
    0.27
    ल्लिंग
    0.27
    Activations Density 1.595%

    No Known Activations