© 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. 85612
    Prev
    Next
    INDEX
    Explanations

    places and proper nouns

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

    The neuron fires on specific named entities and other proper nouns (distinct titles, people’s surnames, organization or product names, scientific names, etc.).

    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
     Could
    -2.92
    "
    -2.84
    a
    -2.67
    ’
    -2.67
    栊
    -2.61
    ने
    -2.50
     This
    -2.42
    蜴
    -2.39
    栳
    -2.33
     мы
    -2.27
    POSITIVE LOGITS
    哢
    2.97
    汌
    2.64
    2.55
     prohibido
    2.52
     absurdo
    2.38
     leur
    2.34
     l
    2.25
     дает
    2.23
     carpenter
    2.20
    豺
    2.19
    Activations Density 0.011%

    No Known Activations