© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128065
    Prev
    Next
    INDEX
    Explanations

    names and associated follow-up words

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

    This neuron detects named entities—especially proper names of people, places, and organizations.

    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
     даже
    -2.28
     chré
    -2.23
     حتی
    -2.06
     ܐ
    -1.92
     sogar
    -1.88
    ׇ
    -1.88
     rekan
    -1.88
    珦
    -1.80
    onOptions
    -1.80
     vielleicht
    -1.77
    POSITIVE LOGITS
    ּוֹ
    2.11
     previously
    1.59
    ִּ
    1.58
    SafeAreaView
    1.56
     vairāk
    1.53
    ְּ
    1.52
     verander
    1.51
    🪛
    1.50
    𓃵
    1.50
     žem
    1.50
    Activations Density 0.103%

    No Known Activations