© 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. 105964
    Prev
    Next
    INDEX
    Explanations

    technical components and devices

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

    This neuron signals mentions of multiple components or quantities (e.g. “plurality,” “multiple,” or plural‐form technical elements) in a description.

    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
     both
    -1.41
    Both
    -1.35
     still
    -1.30
     most
    -1.26
    的所有
    -1.25
    Those
    -1.24
     after
    -1.23
    两者
    -1.22
     two
    -1.19
    实时
    -1.14
    POSITIVE LOGITS
     čier
    1.31
    buenos
    1.23
     okolo
    1.23
     vám
    1.21
    tranh
    1.20
    jesus
    1.19
    rolex
    1.18
    adaş
    1.18
     trám
    1.17
    jangan
    1.16
    Activations Density 0.250%

    No Known Activations