© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 79782
    Prev
    Next
    INDEX
    Explanations

    properties and processes

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

    The neuron detects technical scientific terms that denote experimental parameters or quantitative measures (e.g. decay, stress, predation).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     帳
    -1.23
     síntesis
    -1.21
     Tamanho
    -1.20
     volvió
    -1.20
     again
    -1.17
     Cantidad
    -1.14
     vejo
    -1.14
     Início
    -1.12
    気を
    -1.11
     Adicion
    -1.09
    POSITIVE LOGITS
    ÁRIO
    1.33
    actéristiques
    1.23
    控件
    1.20
    萼
    1.16
    !(:
    1.16
    +)/
    1.16
    ológia
    1.16
     '-')
    1.15
    < 
    1.15
    📱
    1.13
    Activations Density 0.128%

    No Known Activations