© 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. 76442
    Prev
    Next
    INDEX
    Explanations

    controversy

    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
     kötü
    -0.91
     pocit
    -0.86
    ASHION
    -0.84
    stüt
    -0.84
     accidents
    -0.84
     pivotal
    -0.83
    jercicio
    -0.80
    numerus
    -0.80
     dinheiro
    -0.79
    Payer
    -0.79
    POSITIVE LOGITS
    contro
    1.36
     controversy
    1.26
     controversies
    1.23
     Controversy
    1.19
     surrounding
    1.16
     Contro
    1.16
     kontro
    1.13
     controver
    1.13
    Contro
    1.13
    Controversy
    1.11
    Activations Density 0.036%

    No Known Activations