© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57841
    Prev
    Next
    INDEX
    Explanations

    conservative news sources

    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
    ✊
    -0.82
     Episcopal
    -0.79
    nytimes
    -0.75
     mediators
    -0.73
     officiating
    -0.73
     Quakers
    -0.72
    ksin
    -0.71
     BBC
    -0.71
    驯
    -0.70
     Offic
    -0.69
    POSITIVE LOGITS
     conservative
    1.78
     Conservative
    1.65
    Conservative
    1.58
    conservative
    1.58
    保守
    1.52
     conservatives
    1.50
     консер
    1.39
     Conservatives
    1.23
    Conserv
    1.23
    conserv
    1.20
    Activations Density 0.169%

    No Known Activations