© 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. 114198
    Prev
    Next
    INDEX
    Explanations

    Ricky or Roberto followed by a name

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

    This neuron responds to personal proper names (e.g. first names like Ricky or Roberto).

    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
     diversos
    -3.41
     of
    -2.83
    2
    -2.64
     Roughly
    -2.56
     Whether
    -2.56
     ส์
    -2.56
     Personally
    -2.53
     continually
    -2.48
     Emphas
    -2.48
     the
    -2.47
    POSITIVE LOGITS
    Ḱ
    2.31
    韪
    2.20
    i
    2.20
    ❘
    2.08
    י
    2.05
     помощью
    2.02
    ಇ
    2.02
    ſtanding
    2.00
     BUFFER
    2.00
     будет
    2.00
    Activations Density 0.003%

    No Known Activations