© 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. 34-GEMMASCOPE-RES-131K
    7. 98720
    Prev
    Next
    INDEX
    Explanations

    company news and deals

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

    The neuron strongly activates on capitalized proper nouns—names of people, organizations, places, brands, or titles.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     gefähr
    -1.27
     постоянно
    -1.16
    新的
    -1.13
     membunuh
    -1.11
    珦
    -1.10
    ほんと
    -1.09
    諴
    -1.09
     sentía
    -1.07
     neuen
    -1.06
     mitään
    -1.06
    POSITIVE LOGITS
    関する
    1.09
    ⽤
    1.07
    取り組
    1.05
    もあります
    1.01
     قطاع
    1.00
     octavo
    1.00
    AppRoutingModule
    1.00
    ఝ
    0.99
     austria
    0.99
    <bos>
    0.99
    Activations Density 0.310%

    No Known Activations