© 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. 25696
    Prev
    Next
    INDEX
    Explanations

    human rights, equality, discrimination

    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
     fluence
    -0.76
     scipy
    -0.76
    STAN
    -0.75
     Emission
    -0.73
     uo
    -0.72
     vectra
    -0.71
     XXL
    -0.70
    orgeous
    -0.70
     roadster
    -0.70
     clarinet
    -0.70
    POSITIVE LOGITS
     discrimination
    1.93
     Discrimination
    1.81
    discrimination
    1.57
     equality
    1.53
     discriminación
    1.42
     discriminatory
    1.41
     Equality
    1.40
     Human
    1.39
     Equal
    1.35
    Equal
    1.34
    Activations Density 0.020%

    No Known Activations