© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65261
    Prev
    Next
    INDEX
    Explanations

    conservative intellectuals and publications

    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
     rakyat
    -0.96
     Dogecoin
    -0.91
    垫
    -0.88
     Usman
    -0.88
     anarchist
    -0.86
     humanidad
    -0.85
     تصمیم
    -0.84
     सिस्टम
    -0.83
     Astrophys
    -0.83
     kies
    -0.82
    POSITIVE LOGITS
     conservatives
    1.17
     conservative
    1.05
    保守
    1.03
     Intellectual
    1.02
     intellectual
    0.99
    conserv
    0.94
     conservatism
    0.94
     intellectuals
    0.91
    intellectual
    0.91
     AE
    0.89
    Activations Density 0.091%

    No Known Activations