© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103298
    Prev
    Next
    INDEX
    Explanations

    interior secretary and national agencies

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on formal references to government bodies and officials (e.g. “Interior Department,” “Secretary Donald Hodel,” “federal,” “public,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     arty
    -0.73
    ungkan
    -0.69
    Chars
    -0.68
    vensko
    -0.68
    ური
    -0.66
    chars
    -0.65
    angol
    -0.65
    賬
    -0.65
    Cargo
    -0.65
    殓
    -0.65
    POSITIVE LOGITS
     Interior
    2.11
    Interior
    2.05
     NPS
    1.73
    NPS
    1.54
     DOI
    1.47
     interior
    1.40
    INTERIOR
    1.38
    interior
    1.36
    DOI
    1.29
     INTERIOR
    1.25
    Activations Density 0.079%

    No Known Activations