© 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. 22-GEMMASCOPE-RES-131K
    7. 14294
    Prev
    Next
    INDEX
    Explanations

    companies and brands

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

    The main thing this neuron does is detect proper names of organizations, brands, or other named entities in the text.

    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
    んでしょう
    -1.48
    今でも
    -1.48
    今も
    -1.42
    んですか
    -1.39
    をします
    -1.34
     vielfäl
    -1.33
    みましょう
    -1.32
     необхідно
    -1.31
    を行います
    -1.30
    のでしょう
    -1.27
    POSITIVE LOGITS
    vereign
    1.59
    vereignty
    1.52
    dailymail
    1.45
    ckeye
    1.35
    ಎ
    1.34
    isateurs
    1.31
     />
    1.30
    оо
    1.26
    eaways
    1.25
    dienne
    1.23
    Activations Density 0.055%

    No Known Activations