© 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. 59954
    Prev
    Next
    INDEX
    Explanations

    entity followed by descriptor

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

    The neuron is firing on named entities—proper nouns such as place names, organizations, brands, schools, and the like.

    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
     themselves
    -1.23
     vienas
    -1.18
     yourselves
    -1.13
    btnBack
    -1.02
    olverine
    -1.02
    vård
    -0.99
     itself
    -0.96
    laterra
    -0.96
     похоже
    -0.96
     ourselves
    -0.95
    POSITIVE LOGITS
     colleagues
    1.73
     friends
    1.48
     teammates
    1.32
     neighbours
    1.30
     neighbors
    1.30
     duties
    1.29
     avatar
    1.26
     peers
    1.23
     clients
    1.22
     ancestors
    1.20
    Activations Density 0.188%

    No Known Activations