© 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. 22-GEMMASCOPE-RES-131K
    7. 16616
    Prev
    Next
    INDEX
    Explanations

    titles followed by names

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

    This neuron activates on named entities and professional titles (e.g., people’s names and their roles like “Director,” “Chief Executive Officer,” or judge titles).

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    şiv
    -1.10
    Inhoud
    -1.02
    人的
    -0.90
    IDK
    -0.88
    HINT
    -0.88
    ことができ
    -0.88
     yyb
    -0.86
    enada
    -0.85
    Zutaten
    -0.85
     допомогти
    -0.85
    POSITIVE LOGITS
     others
    1.36
     fellow
    1.19
     other
    1.16
    otros
    1.03
    其他人
    1.02
     fühlte
    1.02
    estanden
    1.01
     another
    0.98
    others
    0.98
     antwortete
    0.96
    Activations Density 0.200%

    No Known Activations