© 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. 29086
    Prev
    Next
    INDEX
    Explanations

    Cromwell, Crosby, McLaughlin, peroxidase, Lazar

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

    last names of people.

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

    The neuron fires on personal names—especially surnames of people listed in prose or lists.

    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
    );
    -2.63
    蜮
    -2.59
     Это
    -2.52
    ⽌
    -2.48
    N
    -2.47
    》(
    -2.45
    》（
    -2.42
    .
    -2.41
    ↵↵
    -2.36
    parks
    -2.36
    POSITIVE LOGITS
     unſ
    3.22
     esimerkiksi
    2.92
    pulseira
    2.81
    geſ
    2.75
    快速的
    2.70
     hermanas
    2.67
    縂
    2.64
    ⧠
    2.61
     condamné
    2.58
    手里的
    2.58
    Activations Density 0.027%

    No Known Activations