© 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. 836
    Prev
    Next
    INDEX
    Explanations

    government agencies and services

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

    The neuron detects named organizations or institutional entities (especially government agencies and company names).

    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
    μένος
    -0.97
     autoridades
    -0.97
     стихотво
    -0.96
    ITERIA
    -0.94
    Govt
    -0.93
     pases
    -0.92
     Probl
    -0.92
    
    -0.91
     fuir
    -0.91
     forno
    -0.91
    POSITIVE LOGITS
     health
    1.53
     Environmental
    1.49
     Housing
    1.41
     pension
    1.39
     Health
    1.39
     Police
    1.37
     agricultural
    1.37
     tax
    1.35
     fisheries
    1.34
     Food
    1.33
    Activations Density 0.188%

    No Known Activations