© 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. 22-GEMMASCOPE-RES-131K
    7. 64964
    Prev
    Next
    INDEX
    Explanations

    Opposition Leader

    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
     that
    -1.05
     about
    -1.04
    abou
    -1.00
    ございません
    -0.94
    にあります
    -0.93
    がか
    -0.92
     feltro
    -0.88
     MODER
    -0.88
    fti
    -0.88
    なのです
    -0.88
    POSITIVE LOGITS
     invece
    1.05
    ladora
    1.02
    atuur
    1.00
    ﹕
    0.97
     is
    0.96
    tät
    0.94
    ︰
    0.92
     familien
    0.91
    ě
    0.91
     douleur
    0.90
    Activations Density 0.027%

    No Known Activations