© 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. 22-GEMMASCOPE-RES-131K
    7. 35048
    Prev
    Next
    INDEX
    Explanations

    government and politics

    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
    理事
    -1.25
    돕
    -1.21
     ..."
    -1.19
    "));
    -1.19
    şağı
    -1.16
     (…)
    -1.13
     DIRECTORS
    -1.13
    ❑
    -1.10
    ΠΟ
    -1.09
    哺
    -1.08
    POSITIVE LOGITS
     government
    1.96
     political
    1.83
     governmental
    1.66
     Government
    1.52
     politics
    1.49
     federal
    1.36
     politicians
    1.32
    government
    1.27
     public
    1.25
    political
    1.25
    Activations Density 0.166%

    No Known Activations