© 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. 10-GEMMASCOPE-RES-131K
    7. 69104
    Prev
    Next
    INDEX
    Explanations

    names of people

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

    This neuron activates on people’s names—especially prominent surnames of sports figures and other well-known individuals.

    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
    4
    -1.33
    某些
    -1.29
    Some
    -1.29
     with
    -1.28
     Some
    -1.25
     from
    -1.23
     Another
    -1.22
    2
    -1.21
    t
    -1.19
     between
    -1.16
    POSITIVE LOGITS
     murs
    1.36
    kontak
    1.30
    UTELY
    1.27
     quartiers
    1.27
    ???:
    1.26
     vivent
    1.26
    雠
    1.25
    ":
    1.24
    åter
    1.24
    teten
    1.23
    Activations Density 0.026%

    No Known Activations