© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12860
    Prev
    Next
    INDEX
    Explanations

    time duration measurement

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

    The neuron detects mentions of scientific time‐related measurement terms (e.g. “time constants,” “half‐lives,” “lifetimes,” “relaxation times,” “T₁,” etc.) often paired with numeric values.

    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
    为什么会
    -1.77
     seguente
    -1.63
     something
    -1.59
    怎么可能
    -1.55
     different
    -1.54
     renang
    -1.54
    还不是
    -1.52
     femminile
    -1.52
     toscana
    -1.43
     dirit
    -1.41
    POSITIVE LOGITS
     llenos
    1.68
     diseñados
    1.48
    它
    1.34
    mería
    1.33
     beiden
    1.30
    小伙伴
    1.30
    数据
    1.27
     devenus
    1.26
    ÁCT
    1.25
    时间
    1.24
    Activations Density 0.069%

    No Known Activations