© 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. 92908
    Prev
    Next
    INDEX
    Explanations

    U.S. Representatives

    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
     Senate
    -1.21
    Senate
    -1.05
     senate
    -0.96
    ɡ
    -0.85
    Senator
    -0.78
     senator
    -0.74
    gdx
    -0.73
     senators
    -0.72
     SENATE
    -0.70
     sen
    -0.70
    POSITIVE LOGITS
    VAC
    0.93
     VAC
    0.82
    ␣
    0.81
     subcommittee
    0.79
    Vocal
    0.77
     Labrador
    0.77
    न्द
    0.76
    maßnahmen
    0.73
    Gos
    0.73
     conç
    0.73
    Activations Density 0.029%

    No Known Activations