© 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. 73772
    Prev
    Next
    INDEX
    Explanations

    choosing whom to hire

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

    The neuron fires on mentions of professional service providers (e.g. lawyer, attorney, electrician, plumber).

    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
     felhasznál
    -1.00
    irait
    -0.91
    UPAC
    -0.91
     CHALLENGE
    -0.91
     Accounting
    -0.91
     Opportunities
    -0.90
     Auswirkungen
    -0.90
     proposito
    -0.88
    etor
    -0.88
     Bewußt
    -0.88
    POSITIVE LOGITS
     choosing
    1.52
     their
    1.46
    Choosing
    1.39
     referrals
    1.35
     choose
    1.27
     selecting
    1.25
     whom
    1.23
     vet
    1.22
     hiring
    1.21
     references
    1.20
    Activations Density 0.039%

    No Known Activations