© 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. 85630
    Prev
    Next
    INDEX
    Explanations

    conference sessions Center Calendar

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

    This neuron detects occurrences of the word “conference.”

    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
    埽
    -2.53
     Есть
    -2.41
     was
    -2.36
    縢
    -2.33
     wußte
    -2.30
     antworte
    -2.27
     Можно
    -2.27
    ꦧ
    -2.16
     Более
    -2.13
    IM
    -2.09
    POSITIVE LOGITS
    _
    2.45
    瑧
    2.30
    嗞
    2.08
    鲣
    2.06
     設備
    2.06
    洐
    2.05
     exquisite
    1.98
    ୈ
    1.96
     dekoratif
    1.95
    ❉
    1.95
    Activations Density 0.018%

    No Known Activations