© 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. 34-GEMMASCOPE-RES-131K
    7. 2583
    Prev
    Next
    INDEX
    Explanations

    people in arts and management

    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_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
    blast
    -0.73
     Arzne
    -0.71
    皙
    -0.67
    Blast
    -0.67
     expedient
    -0.66
     środków
    -0.66
     quiche
    -0.66
    گونه
    -0.66
    prep
    -0.66
     blast
    -0.66
    POSITIVE LOGITS
     manager
    0.98
     Manager
    0.97
     Caruso
    0.96
     Managers
    0.96
     managerial
    0.89
    Manager
    0.88
     Repository
    0.85
    estris
    0.85
     managers
    0.85
    manager
    0.84
    Activations Density 0.071%

    No Known Activations