© 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. 22-GEMMASCOPE-RES-131K
    7. 75202
    Prev
    Next
    INDEX
    Explanations

    managing director president chief coach

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

    The neuron strongly activates on proper names and titles identifying individual people.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    当成
    -1.32
    龛
    -1.01
    —
    -0.97
     иной
    -0.96
    '.
    -0.96
    дика
    -0.96
     $-$
    -0.95
    粉色
    -0.94
    €“
    -0.94
    Capacidad
    -0.93
    POSITIVE LOGITS
     said
    1.98
     from
    1.28
     says
    1.16
     forklar
    1.13
     permitirá
    1.13
     sagde
    1.12
     gjø
    1.12
     clearly
    1.11
     couldn
    1.10
     explains
    1.08
    Activations Density 0.023%

    No Known Activations