© 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. 10-GEMMASCOPE-RES-131K
    4. 20461
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

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

    The neuron fires on numeric tokens—especially decimal and integer values—whenever quantities or measurements appear.

    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
     which
    -1.62
    なんですよ
    -1.51
     himo
    -1.46
     mawar
    -1.40
    quelles
    -1.34
    cería
    -1.34
     oxu
    -1.34
     berikan
    -1.33
     различни
    -1.29
     etc
    -1.26
    POSITIVE LOGITS
     mientras
    1.34
    </h1>
    1.34
     .
    1.24
     de
    1.23
    督
    1.18
     a
    1.14
     natomiast
    1.12
     do
    1.12
    ogni
    1.10
     use
    1.09
    Activations Density 0.109%

    No Known Activations