© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 71577
    Prev
    Next
    INDEX
    Explanations

    city names and entities

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

    The neuron fires on the “--” (and similar dashes) that follow news dateline city names (e.g. “DETROIT --”), marking the start of a wire‐style article.

    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
     versátil
    -1.58
     gekozen
    -1.52
     abiye
    -1.52
    摆手
    -1.43
    拍了拍
    -1.42
    jiet
    -1.39
     medlemmer
    -1.38
    ابراین
    -1.38
    pośred
    -1.37
     kontaktu
    -1.36
    POSITIVE LOGITS
     They
    1.98
    >
    1.83
     "
    1.60
     for
    1.54
    дже
    1.48
     deine
    1.40
    .
    1.38
     in
    1.38
     een
    1.37
     way
    1.34
    Activations Density 0.034%

    No Known Activations