© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62494
    Prev
    Next
    INDEX
    Explanations

    financial need and economic status

    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
    Negative Logits
     DUAL
    -0.87
    riture
    -0.83
     ALLOWED
    -0.81
     Doh
    -0.78
    dracht
    -0.78
     グリル
    -0.78
     Hype
    -0.77
     natuur
    -0.77
    Bluetooth
    -0.77
     kompet
    -0.77
    POSITIVE LOGITS
     financial
    1.78
     income
    1.64
     sliding
    1.59
     low
    1.55
     Financial
    1.30
     poverty
    1.23
    貧
    1.22
    Financial
    1.21
     need
    1.20
     hardship
    1.20
    Activations Density 0.028%

    No Known Activations