© 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. 10-GEMMASCOPE-RES-131K
    7. 102691
    Prev
    Next
    INDEX
    Explanations

    people in relation to countries

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

    The neuron flags mentions of a nation’s populace expressed as “[Nationality] 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_10/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
     using
    -2.06
     as
    -1.94
     because
    -1.74
     Without
    -1.70
     two
    -1.70
     from
    -1.69
     after
    -1.68
     Using
    -1.65
     says
    -1.63
     taking
    -1.61
    POSITIVE LOGITS
     HUNT
    1.62
     zoude
    1.55
    aimeJ
    1.55
     urgente
    1.52
    niti
    1.48
     kader
    1.48
     bougies
    1.46
    
    1.44
     diki
    1.42
    蕺
    1.42
    Activations Density 0.017%

    No Known Activations