© 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. 41419
    Prev
    Next
    INDEX
    Explanations

    your website, forum, products, or designs

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

    The neuron fires on second‐person references—especially “you” or “your” plus the noun that follows—i.e. when the text directly addresses 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_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
    Sú
    -1.10
    Unternehmen
    -1.07
     bahkan
    -1.04
    ㅿ
    -1.03
     even
    -1.03
     quatrième
    -1.02
    即将
    -1.00
    IGATION
    -1.00
    お待ちしております
    -0.98
     طریق
    -0.96
    POSITIVE LOGITS
     since
    1.31
    Since
    1.24
    since
    1.20
     depuis
    1.12
    präch
    1.02
     waaronder
    1.02
    andalf
    1.00
    {
    0.99
    cestor
    0.99
    包含
    0.98
    Activations Density 0.099%

    No Known Activations