© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60457
    Prev
    Next
    INDEX
    Explanations

    groups of people and their communities

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     ciudad
    -0.90
    ftig
    -0.89
     oscuro
    -0.85
    centages
    -0.84
     referencia
    -0.84
     information
    -0.82
     refugio
    -0.82
     nivel
    -0.81
    ország
    -0.81
    ordinal
    -0.80
    POSITIVE LOGITS
     population
    2.98
     community
    2.25
     cohort
    2.17
    population
    1.95
     populace
    1.76
     workforce
    1.75
     electorate
    1.70
    Population
    1.61
     corps
    1.59
     fanbase
    1.56
    Activations Density 0.128%

    No Known Activations