© 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. 48647
    Prev
    Next
    INDEX
    Explanations

    social protection, inclusion, justice, development

    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
     Fever
    -0.77
    痙
    -0.77
    ündete
    -0.76
    oltà
    -0.73
    ändigkeit
    -0.71
     maksimal
    -0.71
     maig
    -0.70
    を失
    -0.69
    uclear
    -0.69
     lavabo
    -0.68
    POSITIVE LOGITS
     захи
    0.98
     scour
    0.96
     protection
    0.94
     inclusion
    0.90
     evil
    0.86
    وذ
    0.84
     and
    0.83
     mobilization
    0.83
     Protection
    0.83
    oprot
    0.83
    Activations Density 0.021%

    No Known Activations