© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 98262
    Prev
    Next
    INDEX
    Explanations

    URLs and websites

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

    The neuron is selectively activating on named entities and specialized proper nouns—titles of people, organizations, projects, places, 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_22/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
     Ciné
    -1.19
     pandemia
    -1.16
     reaf
    -1.04
     ridic
    -1.04
     ratific
    -1.04
     rocha
    -1.04
     farmacia
    -1.04
    ☆☆☆☆☆
    -1.04
     Condé
    -1.03
     Futsal
    -1.03
    POSITIVE LOGITS
     websites
    1.25
     menciona
    1.21
     supaya
    1.19
     episodes
    1.18
     utilizó
    1.17
    เยอะ
    1.14
     mencionó
    1.13
     habló
    1.13
     gutem
    1.13
     mentioned
    1.11
    Activations Density 0.004%

    No Known Activations