© 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. 34-GEMMASCOPE-RES-131K
    7. 63761
    Prev
    Next
    INDEX
    Explanations

    socio-economic insecurity and livelihoods

    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
     readline
    -0.81
     halte
    -0.75
     dieci
    -0.73
     circulaire
    -0.70
     triom
    -0.70
    finale
    -0.69
     liné
    -0.68
    王者
    -0.68
     juvenile
    -0.68
    Joystick
    -0.68
    POSITIVE LOGITS
     household
    1.63
     households
    1.61
     assets
    1.54
     livelihoods
    1.41
     Household
    1.40
     Households
    1.34
     asset
    1.34
     livelihood
    1.30
     vulnerability
    1.29
     coping
    1.27
    Activations Density 0.016%

    No Known Activations