© 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. 10-GEMMASCOPE-RES-131K
    4. 42598
    Prev
    Next
    INDEX
    Explanations

    names after common words

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

    The neuron fires on capitalized named entities—proper names of people, places, organizations, etc.

    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
     is
    -1.77
     we
    -1.47
     you
    -1.40
    ということで
    -1.35
     samochód
    -1.32
    夯
    -1.32
     znacz
    -1.31
    と思
    -1.30
     inspiradoras
    -1.30
     gerçek
    -1.23
    POSITIVE LOGITS
     in
    1.44
     diny
    1.30
     koel
    1.28
    /***
    
    1.25
    joyed
    1.24
    eeeee
    1.23
     gonz
    1.23
    hever
    1.23
     nasi
    1.23
     jule
    1.22
    Activations Density 0.022%

    No Known Activations