© 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. 10-GEMMASCOPE-RES-131K
    7. 42606
    Prev
    Next
    INDEX
    Explanations

    you followed by modal verbs

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

    The neuron fires on direct second‐person address, specifically the word “you.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    :
    -1.60
    (
    -1.55
     which
    -1.52
    the
    -1.45
    raisers
    -1.45
    ;
    -1.42
     où
    -1.39
    where
    -1.39
     the
    -1.38
      
    -1.36
    POSITIVE LOGITS
    (!__
    2.27
     azonban
    2.08
    selbe
    1.80
     něj
    1.73
    "]();
    1.70
     comienzos
    1.70
     *)__
    1.65
    Hozzá
    1.65
     (!__
    1.64
    蓠
    1.63
    Activations Density 0.049%

    No Known Activations