© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59499
    Prev
    Next
    INDEX
    Explanations

    data provider or filler

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

    This neuron activates on terms related to data-bound grid views and data operations (e.g. datagrid, dataset, data adapter, Fill).

    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
     hvilke
    -1.28
    你怎么
    -1.28
    友人
    -1.26
     проектов
    -1.23
    你现在
    -1.22
    邁
    -1.21
    Sådan
    -1.20
    ｵ
    -1.19
     bytu
    -1.19
     procesu
    -1.19
    POSITIVE LOGITS
     bajo
    1.37
     isang
    1.21
     Beide
    1.16
     zeigt
    1.14
    釉
    1.13
     firebaseConfig
    1.12
    ずみ
    1.09
    lossene
    1.09
    ilhas
    1.09
    ."
    1.09
    Activations Density 0.063%

    No Known Activations