© 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. 34-GEMMASCOPE-RES-131K
    7. 49017
    Prev
    Next
    INDEX
    Explanations

    US Congress 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
    ⊨
    -0.82
    ◤
    -0.80
     Stornier
    -0.80
    Optional
    -0.78
    ");
    -0.74
    Город
    -0.73
    VG
    -0.72
     Seneca
    -0.71
    glClear
    -0.71
    قیمت
    -0.70
    POSITIVE LOGITS
     Congressman
    3.36
     congressman
    3.28
     congress
    2.88
     Congress
    2.80
    Congress
    2.66
     Rep
    2.64
     Representative
    2.63
    congress
    2.53
     House
    2.44
    Representative
    2.33
    Activations Density 0.101%

    No Known Activations