© 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. 50040
    Prev
    Next
    INDEX
    Explanations

    criticism and critique of others

    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
     parlamento
    -0.84
    icoot
    -0.82
    흥
    -0.82
     credo
    -0.81
     récit
    -0.81
    惩
    -0.80
    ttl
    -0.79
     plata
    -0.78
    加藤
    -0.78
     civilised
    -0.76
    POSITIVE LOGITS
     criticism
    5.34
     critics
    4.97
     criticisms
    4.47
     Critics
    3.97
     criticized
    3.97
     critique
    3.81
     critic
    3.78
     Criticism
    3.77
     criticised
    3.63
     criticize
    3.55
    Activations Density 0.150%

    No Known Activations