© 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. 19206
    Prev
    Next
    INDEX
    Explanations

    titles and names

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

    The neuron detects multi‐word proper names and titles—e.g. film titles, organization or event names, and other named entities.

    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
     multiuso
    -1.74
     chimie
    -1.72
     bricola
    -1.69
     evangé
    -1.68
     assistente
    -1.67
     lanterna
    -1.67
     anderen
    -1.66
     tortura
    -1.65
     patrie
    -1.65
     manuten
    -1.65
    POSITIVE LOGITS
     one
    1.91
     will
    1.90
     our
    1.76
     now
    1.70
    ]}\
    1.64
     what
    1.63
     not
    1.60
     so
    1.60
     to
    1.59
     —
    1.59
    Activations Density 0.060%

    No Known Activations