© 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. 54369
    Prev
    Next
    INDEX
    Explanations

    delta (δ) in science and math

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

    The neuron responds to every occurrence of the word “delta,” i.e. it detects the token “delta.”

    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
     This
    -2.61
     Now
    -2.48
     unteren
    -2.34
    u
    -2.28
    ↵↵
    -2.22
     opportune
    -2.22
     einzigen
    -2.20
     blazing
    -2.19
     inept
    -2.19
    se
    -2.16
    POSITIVE LOGITS
    鼇
    2.84
    觧
    2.83
    titial
    2.78
    
    2.72
    蛩
    2.64
    蛲
    2.61
     内衣
    2.61
    \
    2.59
    颡
    2.56
    ᯾
    2.52
    Activations Density 0.004%

    No Known Activations