© 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. 34-GEMMASCOPE-RES-131K
    7. 49854
    Prev
    Next
    INDEX
    Explanations

    politician names and titles

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

    The neuron fires strongly on named entities—especially names and titles of politicians or government officials.

    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
    irled
    -0.74
     Silla
    -0.73
    descripcion
    -0.73
    XIM
    -0.72
    -//
    -0.71
     fum
    -0.69
    casting
    -0.69
    hibian
    -0.68
    izaje
    -0.68
     Много
    -0.68
    POSITIVE LOGITS
     られる
    0.80
     Travail
    0.75
     Harlem
    0.75
     believes
    0.72
     mukana
    0.71
     Ouvrez
    0.71
     ceinture
    0.71
    раи
    0.70
     disciplina
    0.69
     collegiate
    0.69
    Activations Density 0.022%

    No Known Activations