© 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. 104335
    Prev
    Next
    INDEX
    Explanations

    tools and materials

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

    The neuron primarily activates on numeric expressions and quantified information—i.e. numbers and measurements—in the text.

    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
     your
    -1.61
     оружи
    -1.59
     you
    -1.40
    וּ
    -1.38
     hígado
    -1.34
     fizik
    -1.33
    证件
    -1.31
    UTION
    -1.29
     становника
    -1.27
    ּוֹ
    -1.27
    POSITIVE LOGITS
    ׇ
    1.54
     about
    1.47
     ویتامین
    1.40
     ᾿
    1.33
     ингреди
    1.32
     paradiso
    1.32
    =$?
    1.30
     princesas
    1.29
     diadakan
    1.27
     poter
    1.27
    Activations Density 0.055%

    No Known Activations