© 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. 22-GEMMASCOPE-RES-131K
    4. 104295
    Prev
    Next
    INDEX
    Explanations

    names and titles

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

    The neuron triggers on capitalized named-entity tokens—proper names, titles, and other named references.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    uvre
    -1.21
    太多
    -1.06
     gemessen
    -1.03
    !!!!!!!
    -1.01
    !!!!!!
    -1.01
     wichtigste
    -1.00
     youngsters
    -1.00
     splendid
    -1.00
     erstes
    -0.99
     hätten
    -0.98
    POSITIVE LOGITS
    исто
    1.28
    ždý
    1.20
     religieuse
    1.17
     before
    1.09
     chré
    1.09
    tür
    1.08
    TLDR
    1.06
     fondament
    1.05
     Greece
    1.05
    ㄎ
    1.04
    Activations Density 0.023%

    No Known Activations