© 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. 128007
    Prev
    Next
    INDEX
    Explanations

    DBA, Pogba, StatusEnum, 美女

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

    The neuron is looking for named entities—proper nouns and acronyms (e.g. surnames, organization abbreviations).

    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
    轳
    -2.94
    n
    -2.81
     ünl
    -2.47
    dzić
    -2.44
    媖
    -2.41
    ját
    -2.36
    糖尿病
    -2.34
    ⎘
    -2.31
    읊
    -2.30
    廨
    -2.28
    POSITIVE LOGITS
    0
    2.95
    2
    2.73
     outras
    2.55
    </h4>
    2.42
     
    2.36
    一点点
    2.27
    ”。
    2.23
    “
    2.22
    其他的
    2.22
    ,”
    2.22
    Activations Density 0.030%

    No Known Activations