© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65004
    Prev
    Next
    INDEX
    Explanations

    staff and employees

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     什么
    -0.92
     raggi
    -0.91
     something
    -0.91
     hagy
    -0.90
    imgs
    -0.86
     leur
    -0.85
     invitado
    -0.85
    levering
    -0.84
     su
    -0.84
     after
    -0.84
    POSITIVE LOGITS
     who
    1.91
     staff
    1.49
     offices
    1.22
    aisons
    1.16
     gainera
    1.13
     onderzoek
    1.13
    staff
    1.11
     office
    1.11
     tých
    1.07
    
    1.05
    Activations Density 0.035%

    No Known Activations