© 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. 10-GEMMASCOPE-RES-131K
    7. 44748
    Prev
    Next
    INDEX
    Explanations

    politicians by party

    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_10/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
    !
    -1.91
    </strong>
    -1.54
    ieteur
    -1.52
    ࿚
    -1.50
     your
    -1.49
    z
    -1.48
    ！（
    -1.46
    ig
    -1.45
    +"'
    -1.41
    各大
    -1.41
    POSITIVE LOGITS
    簠
    1.92
    drake
    1.72
    鬭
    1.68
     of
    1.63
     afspraak
    1.61
    .
    1.49
    despite
    1.48
     than
    1.48
    albeit
    1.48
    nse
    1.48
    Activations Density 0.008%

    No Known Activations