© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102888
    Prev
    Next
    INDEX
    Explanations

    application or use

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

    The neuron fires on strongly evaluative or promotional words—especially positive adjectives and adverbs that emphasize strength, excellence, or effectiveness.

    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
     مناط
    -1.54
     eksklu
    -1.36
    回目
    -1.31
     icônes
    -1.29
    回目の
    -1.27
     переписи
    -1.23
     quartiere
    -1.23
     tâches
    -1.23
    ługa
    -1.21
    ximity
    -1.20
    POSITIVE LOGITS
     sítio
    1.27
     ۲۰
    1.23
    걀
    1.23
     =
    1.21
    5
    1.20
    못
    1.19
     success
    1.19
     fashioned
    1.18
     себя
    1.16
    ündigung
    1.16
    Activations Density 0.071%

    No Known Activations