© 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. 90578
    Prev
    Next
    INDEX
    Explanations

    professions and their duties

    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
     antwortete
    -0.94
     Angebote
    -0.93
    iertos
    -0.92
    uerdo
    -0.91
     workers
    -0.90
     Einrichtungen
    -0.87
     Hauses
    -0.85
     warmen
    -0.84
     veröffentlich
    -0.83
    szön
    -0.81
    POSITIVE LOGITS
     role
    1.13
    ship
    1.04
     training
    1.01
    SHIP
    0.99
    Dashboard
    0.96
    ское
    0.92
    िंग
    0.91
    hood
    0.90
    hing
    0.89
     duties
    0.88
    Activations Density 0.098%

    No Known Activations