© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104389
    Prev
    Next
    INDEX
    Explanations

    Core MVC

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

    technical or legal abbreviations and acronyms in formal documents.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron is triggered by capitalized terms—proper names, acronyms, headings, and other title-case or all-caps tokens.

    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
     noten
    -1.45
     articoli
    -1.45
    iyle
    -1.38
     tecnici
    -1.35
    詎
    -1.33
     tecnologie
    -1.32
    branche
    -1.29
     comunicazione
    -1.28
    gucig
    -1.27
     needed
    -1.26
    POSITIVE LOGITS
     již
    1.49
     are
    1.40
    /
    1.38
    рыва
    1.35
     ļoti
    1.34
     And
    1.34
    ↵↵
    1.33
     asisti
    1.32
     at
    1.27
     say
    1.23
    Activations Density 0.192%

    No Known Activations