© 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. 70874
    Prev
    Next
    INDEX
    Explanations

    origin or birth

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

    The neuron fires on mentions of a “born” statement indicating when something was created or originated.

    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
    說是
    -1.82
    ambiental
    -1.76
    اً
    -1.72
    上に
    -1.67
    ͘
    -1.66
    ஂ
    -1.65
    使用的
    -1.63
    so
    -1.59
    verter
    -1.58
    cisive
    -1.57
    POSITIVE LOGITS
    瘸
    1.54
     zweimal
    1.48
     abarca
    1.46
    ,
    1.46
    tedrale
    1.41
    Académie
    1.40
    艫
    1.38
     muut
    1.34
    Acqu
    1.34
     благодаря
    1.34
    Activations Density 0.022%

    No Known Activations