© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109201
    Prev
    Next
    INDEX
    Explanations

    government offices and roles

    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
    sweise
    -0.88
     сок
    -0.77
     APR
    -0.74
    Lens
    -0.71
    所得
    -0.70
     besö
    -0.69
     '.'
    -0.69
    ütü
    -0.68
    Glen
    -0.68
     fli
    -0.68
    POSITIVE LOGITS
     OMB
    2.38
     Office
    2.05
    OMB
    1.88
    Office
    1.53
     budget
    1.51
     Budget
    1.41
     OFFICE
    1.39
    Budget
    1.29
     office
    1.28
     omb
    1.25
    Activations Density 0.044%

    No Known Activations