© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77525
    Prev
    Next
    INDEX
    Explanations

    economy and society

    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
    aterial
    -1.16
    apartamento
    -1.05
    これが
    -1.05
    ָם
    -1.02
    paisaje
    -0.99
    などを
    -0.96
     câteva
    -0.94
    EXPERIMENTAL
    -0.94
    itado
    -0.93
     Ereignisse
    -0.93
    POSITIVE LOGITS
     society
    2.05
     overall
    1.63
     morale
    1.59
     economy
    1.41
     both
    1.40
     the
    1.38
     Society
    1.31
     democracy
    1.30
     taxpayers
    1.27
     SOCIETY
    1.26
    Activations Density 0.053%

    No Known Activations