© 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. 105427
    Prev
    Next
    INDEX
    Explanations

    names of places or media

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

    This neuron fires on capitalized proper names—especially personal names and titles of films or TV shows.

    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
     alojamientos
    -1.40
     regalías
    -1.36
     Garantía
    -1.34
    營業時間
    -1.32
     balcón
    -1.30
     jednej
    -1.28
    だけではなく
    -1.24
     ſol
    -1.23
     Tamaño
    -1.23
     pracuje
    -1.23
    POSITIVE LOGITS
     all
    2.17
     any
    1.73
     an
    1.67
     three
    1.60
     in
    1.57
     their
    1.56
     a
    1.55
     also
    1.48
     at
    1.43
     was
    1.41
    Activations Density 0.057%

    No Known Activations