© 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. 22-GEMMASCOPE-RES-131K
    7. 13208
    Prev
    Next
    INDEX
    Explanations

    job titles after roles/departments

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

    The neuron detects tokens naming organizational units, departments, programs, or management/operations divisions.

    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
    がなく
    -1.19
    他の
    -1.18
    animity
    -1.16
     juſt
    -1.12
     모든
    -1.10
     如果
    -1.09
    genöss
    -1.06
     perifer
    -1.05
     এবং
    -1.05
    そして
    -1.05
    POSITIVE LOGITS
     manager
    1.27
     director
    1.21
     chief
    1.16
     constantemente
    1.11
     principle
    1.09
     Chief
    1.09
     supervisor
    1.09
     whatnot
    1.09
     lead
    1.06
     coordinator
    1.05
    Activations Density 0.047%

    No Known Activations