© 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. 40770
    Prev
    Next
    INDEX
    Explanations

    favorite bacteria or topics

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

    This neuron activates for specialized terminology and named entities across different domains, particularly words related to medical terms, scientific concepts, and fan favorites.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     you
    -1.60
     здесь
    -1.42
     каждого
    -1.33
    踐
    -1.30
    ній
    -1.29
     мы
    -1.26
     dibawah
    -1.22
    ↵↵
    -1.21
    ляет
    -1.21
     in
    -1.19
    POSITIVE LOGITS
     meines
    1.41
    után
    1.35
     miten
    1.33
     adoro
    1.27
    牖
    1.27
     ulub
    1.26
     科技
    1.24
     présidenti
    1.23
     fortsatt
    1.23
     спросил
    1.23
    Activations Density 0.076%

    No Known Activations