© 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. 65941
    Prev
    Next
    INDEX
    Explanations

    social protection and conditional cash

    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
     estan
    -0.74
    рово
    -0.74
    onoi
    -0.72
     Fue
    -0.72
     ود
    -0.70
    wieś
    -0.69
     etme
    -0.69
    bitt
    -0.68
    inex
    -0.67
     tū
    -0.67
    POSITIVE LOGITS
     Conditional
    1.27
     cash
    1.19
    Conditional
    1.17
     Bolsa
    1.13
     beneficiaries
    1.09
    conditional
    1.07
    Cash
    1.05
     conditional
    1.05
     social
    1.03
    Social
    1.01
    Activations Density 0.003%

    No Known Activations