© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67209
    Prev
    Next
    INDEX
    Explanations

    internet protocols and servers

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

    The neuron fires on second‐person pronouns (e.g. “您” in Chinese, “anata” in Japanese, etc.), i.e. tokens meaning “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
     Когда
    -1.59
     เพราะ
    -1.50
    valho
    -1.48
    gettes
    -1.45
     Posteriormente
    -1.44
     Sedangkan
    -1.36
     Defenders
    -1.34
    اولة
    -1.31
     Bahkan
    -1.31
     После
    -1.31
    POSITIVE LOGITS
    </h1>
    1.63
     paillettes
    1.49
    
    1.44
    jaqueta
    1.39
    ٣
    1.38
     alpes
    1.37
    是怎么
    1.36
    哢
    1.34
     herv
    1.34
    ⬯
    1.34
    Activations Density 0.021%

    No Known Activations