© 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. 21726
    Prev
    Next
    INDEX
    Explanations

    entities and organizations

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

    The neuron fires on occurrences of the word “entity” (especially its plural form “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
     ſame
    -2.36
    tienen
    -2.05
    鱚
    -2.00
    思议
    -1.99
    ."
    -1.92
     этими
    -1.88
    кроссовки
    -1.85
    homonymie
    -1.84
     wasting
    -1.80
     taal
    -1.80
    POSITIVE LOGITS
     proactively
    2.31
     ‘
    2.28
    ta
    2.19
    ’
    2.19
     entities
    2.17
    迨
    2.11
    峮
    2.11
    他也
    1.99
    くれた
    1.95
    ⚋
    1.92
    Activations Density 0.007%

    No Known Activations