© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12922
    Prev
    Next
    INDEX
    Explanations

    Ryan Reynolds, Dwyane Wade, Hobbs

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

    This neuron fires on standalone capitalized named entities—proper nouns like person names, film titles, or brand names.

    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
    as
    -1.27
    Semua
    -1.26
    ldots
    -1.26
     jost
    -1.25
    ли
    -1.25
    ."
    -1.24
    仍然
    -1.21
    0
    -1.20
     диска
    -1.20
    é
    -1.20
    POSITIVE LOGITS
     chimenea
    1.42
    ellt
    1.41
     Añade
    1.36
    umentar
    1.36
    GEBURTS
    1.30
     vocabulary
    1.29
    Vocabulary
    1.29
     tématu
    1.28
    跣
    1.27
     údaj
    1.26
    Activations Density 0.015%

    No Known Activations