© 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. 22-GEMMASCOPE-RES-131K
    7. 75330
    Prev
    Next
    INDEX
    Explanations

    leftist and communist topics

    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_22/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
     polvere
    -1.14
     Fucking
    -1.06
     sexist
    -1.03
     sexism
    -1.00
     fucked
    -0.99
     homophobic
    -0.95
     assholes
    -0.95
     hoffen
    -0.94
    比較的
    -0.93
     austerity
    -0.93
    POSITIVE LOGITS
     Biden
    1.32
     taxpayer
    1.18
     Democrat
    1.05
    ardonnay
    1.00
     左
    0.99
     Chairman
    0.97
    そうですね
    0.95
     Hispanic
    0.94
     Communist
    0.94
    ifornia
    0.94
    Activations Density 0.224%

    No Known Activations