© 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. 107159
    Prev
    Next
    INDEX
    Explanations

    association, federation, lobbying

    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
     bruja
    -0.73
    toupper
    -0.73
    breitung
    -0.68
    王朝
    -0.67
    奂
    -0.66
     UNESCO
    -0.66
     Einkommen
    -0.66
     novela
    -0.65
    Como
    -0.65
     Felton
    -0.64
    POSITIVE LOGITS
     lobbying
    1.02
     AFL
    1.02
     Association
    0.99
    lobby
    0.94
     federation
    0.94
     Biotechnology
    0.93
    AFL
    0.92
     Federation
    0.91
     ASSOCIATION
    0.91
     lobby
    0.91
    Activations Density 0.062%

    No Known Activations