© 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. 104836
    Prev
    Next
    INDEX
    Explanations

    towns, parishes, states

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

    The neuron activates on proper names and other capitalized named entities—people, places, 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
    enerbahçe
    -1.44
    en
    -1.42
     acoged
    -1.38
    onedDateTime
    -1.36
     potrafi
    -1.34
     говорит
    -1.34
    哐
    -1.34
     cuarzo
    -1.34
    ございません
    -1.31
    er
    -1.27
    POSITIVE LOGITS
     tiveram
    1.56
    </u>
    1.38
     dão
    1.34
    </em>
    1.30
     ficaram
    1.29
    必须
    1.29
     Faster
    1.27
     herausgegeben
    1.27
     passaram
    1.27
     encontram
    1.25
    Activations Density 0.002%

    No Known Activations