© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 15320
    Prev
    Next
    INDEX
    Explanations

    keeping or maintaining things

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

    The neuron is spotting mentions of maintaining or keeping inventories, lists, or subscriptions (e.g., phrases like “maintain an inventory,” “keep a list,” “maintain a subscription”).

    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
     Technologien
    -1.38
    ("}\
    -1.23
     Processing
    -1.23
    koľ
    -1.22
     eerst
    -1.21
     Golfo
    -1.20
     هنوز
    -1.19
    ziem
    -1.18
    早速
    -1.17
    väll
    -1.16
    POSITIVE LOGITS
     on
    1.86
     for
    1.60
     também
    1.34
     in
    1.31
     también
    1.25
     inoltre
    1.24
     coisas
    1.23
    esistenza
    1.17
     във
    1.17
     tất
    1.16
    Activations Density 0.052%

    No Known Activations