© 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. 10-GEMMASCOPE-RES-131K
    7. 21509
    Prev
    Next
    INDEX
    Explanations

    US government departments

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

    This neuron fires on mentions of U.S. government departments (e.g. “Department” and the associated agency name).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    GraphicsUnit
    -1.60
    );
    -1.54
     Füßen
    -1.48
    rightarrow
    -1.47
     continuar
    -1.44
    They
    -1.43
    "
    -1.41
    ਂ
    -1.41
    </sup>
    -1.41
    gemeester
    -1.40
    POSITIVE LOGITS
    istungen
    1.64
     inalámb
    1.54
     piese
    1.52
     概要
    1.47
     espectro
    1.47
     内衣
    1.44
    Szer
    1.43
    塤
    1.41
     チラ
    1.40
     recount
    1.39
    Activations Density 0.030%

    No Known Activations