© 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. 75071
    Prev
    Next
    INDEX
    Explanations

    Pharmaceutical Industries or names

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

    names of professional athletes and sports figures.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron responds to named entities—especially capitalized proper names of people and organizations.

    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
    阖
    -1.47
     of
    -1.47
    rijving
    -1.38
     maladie
    -1.34
    НОСТИ
    -1.27
     to
    -1.27
     not
    -1.25
     flot
    -1.23
     *
    -1.21
     duas
    -1.21
    POSITIVE LOGITS
     quando
    1.39
     falschen
    1.38
     Eigentü
    1.37
     damaligen
    1.36
     controllare
    1.34
    亊
    1.34
    mbgg
    1.33
    舠
    1.30
    ：“
    1.30
     cuando
    1.30
    Activations Density 0.054%

    No Known Activations