© 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. 73490
    Prev
    Next
    INDEX
    Explanations

    reality tv housewives

    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
    orrhage
    -0.86
     disguise
    -0.85
     vérification
    -0.84
     discouraging
    -0.84
    ☌
    -0.81
     rarer
    -0.80
     élect
    -0.80
     eyeing
    -0.79
     scuro
    -0.79
     disheart
    -0.78
    POSITIVE LOGITS
     Bravo
    1.57
     Season
    1.48
     filming
    1.26
    Bravo
    1.25
     season
    1.23
    Season
    1.23
     episode
    1.22
     producers
    1.20
     Housewives
    1.16
    season
    1.15
    Activations Density 0.021%

    No Known Activations