© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90039
    Prev
    Next
    INDEX
    Explanations

    staff and prices

    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
    нется
    -1.13
    neling
    -1.04
    genicity
    -1.03
    alucía
    -1.02
    我们
    -1.01
    kitab
    -1.01
    opoulos
    -0.98
     pembelajaran
    -0.97
    ternut
    -0.96
    preneurs
    -0.95
    POSITIVE LOGITS
     they
    1.91
     prices
    1.84
    Their
    1.75
     staff
    1.73
    They
    1.59
     their
    1.56
    Prices
    1.48
     employees
    1.48
    prices
    1.35
     Prices
    1.33
    Activations Density 0.006%

    No Known Activations