© 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. 53986
    Prev
    Next
    INDEX
    Explanations

    company advice

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

    The neuron detects the boilerplate salary‐figure disclaimer sections commonly found in job listings.

    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
    terscotch
    -0.93
    tahan
    -0.85
    つは
    -0.82
     givet
    -0.82
     argumentos
    -0.81
    upuesto
    -0.80
    委托
    -0.80
    gili
    -0.80
    теры
    -0.79
    systemctl
    -0.79
    POSITIVE LOGITS
    Pros
    1.25
     Pros
    1.24
     employee
    1.16
    Employee
    1.13
     former
    1.11
     employees
    1.07
     pros
    1.05
     advice
    1.04
     Glass
    1.01
     company
    0.99
    Activations Density 0.005%

    No Known Activations