© 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. 22-GEMMASCOPE-RES-131K
    7. 66972
    Prev
    Next
    INDEX
    Explanations

    government roles and departments

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

    This neuron is broadly detecting common English function words (e.g. articles, prepositions, conjunctions).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ובה
    -1.14
     konfig
    -1.12
    なるべく
    -1.12
     เปิด
    -1.10
    ほとん
    -1.09
     ekos
    -1.09
    どっち
    -1.09
    owana
    -1.09
     elegante
    -1.08
     spektak
    -1.08
    POSITIVE LOGITS
     health
    1.31
     its
    1.29
     finance
    1.26
     maintenance
    1.23
     marketing
    1.21
     compliance
    1.20
     Health
    1.20
     food
    1.19
     computer
    1.19
     operations
    1.18
    Activations Density 0.044%

    No Known Activations