© 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. 73782
    Prev
    Next
    INDEX
    Explanations

    Mexican politicians and their state affiliations

    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
     operativos
    -0.77
    どく
    -0.75
    cznym
    -0.75
     estratégico
    -0.75
     versátil
    -0.73
    盡
    -0.73
     试
    -0.72
     Sinaloa
    -0.72
    uktur
    -0.71
    deckt
    -0.70
    POSITIVE LOGITS
     colonies
    0.82
     COLON
    0.82
     colony
    0.82
     Colonies
    0.80
     colonia
    0.77
    colon
    0.75
     colonial
    0.74
     cranial
    0.74
     colon
    0.74
     exterior
    0.73
    Activations Density 0.013%

    No Known Activations