© 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. 1442
    Prev
    Next
    INDEX
    Explanations

    House and Senate committees

    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
     hangat
    -0.70
     leksikon
    -0.68
    Palace
    -0.66
    监狱
    -0.66
     Croix
    -0.66
     Dumont
    -0.65
    abag
    -0.65
     spong
    -0.65
    pakt
    -0.65
    .....
    -0.64
    POSITIVE LOGITS
     committee
    1.84
     committees
    1.71
     Committee
    1.54
    Committee
    1.39
     COMMITTEE
    1.38
     комите
    1.34
    committee
    1.34
     Committees
    1.30
     Armed
    1.19
     Appropriations
    1.14
    Activations Density 0.041%

    No Known Activations