© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30495
    Prev
    Next
    INDEX
    Explanations

    people's names

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

    This neuron activates on tokens that are parts of proper personal names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ━━━
    -1.02
    露天
    -0.98
    ENCES
    -0.96
     סס
    -0.93
     gout
    -0.92
     cerr
    -0.90
     executives
    -0.89
     opium
    -0.88
     editors
    -0.88
    GeoNames
    -0.88
    POSITIVE LOGITS
     erila
    1.01
     desmotiv
    0.92
     różne
    0.88
    cinct
    0.88
     sostu
    0.87
    烬
    0.85
     said
    0.85
    haviour
    0.85
    不同
    0.85
     sigue
    0.84
    Activations Density 0.139%

    No Known Activations