© 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. 41973
    Prev
    Next
    INDEX
    Explanations

    follow-up periods

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

    The neuron detects mentions of “follow-up” (and associated numeric follow-up durations) in clinical study reports.

    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
     about
    -3.00
     not
    -2.08
     no
    -1.79
     \
    -1.78
     It
    -1.77
     to
    -1.63
     There
    -1.53
     <
    -1.52
    ↵
    -1.50
     who
    -1.49
    POSITIVE LOGITS
    手绘
    1.74
    
    1.72
     ceket
    1.69
    Jawaban
    1.66
     validés
    1.66
    ーズン
    1.66
    ผม
    1.65
    仳
    1.65
    เพราะ
    1.64
    ごとの
    1.63
    Activations Density 0.039%

    No Known Activations