© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 98811
    Prev
    Next
    INDEX
    Explanations

    first names or name endings

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

    The neuron is primarily activated by human personal names (proper names) in the text.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     như
    -1.39
    飓
    -1.32
     técnicos
    -1.30
    違います
    -1.29
    {})
    -1.25
    -”
    -1.24
     each
    -1.23
     santo
    -1.20
    鹦
    -1.20
    ユーザ
    -1.19
    POSITIVE LOGITS
     who
    1.51
    intelligible
    1.34
    featureID
    1.30
    gestone
    1.29
    ktionen
    1.27
    skraft
    1.27
     about
    1.25
    JECT
    1.24
    katkan
    1.24
    AppCompatTheme
    1.23
    Activations Density 0.076%

    No Known Activations