© 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. 22-GEMMASCOPE-RES-131K
    7. 11224
    Prev
    Next
    INDEX
    Explanations

    top management and executives

    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
     že
    -1.26
     more
    -1.23
    Others
    -1.11
    :"-
    -1.10
    ihnach
    -1.09
    afterEach
    -1.09
    ׇ
    -1.09
     htons
    -1.08
    ='\
    -1.05
     بعد
    -1.04
    POSITIVE LOGITS
     of
    1.70
     level
    1.67
     leadership
    1.66
     executive
    1.48
     executives
    1.41
     who
    1.29
    trio
    1.16
     positions
    1.15
     décision
    1.11
     dirigeants
    1.08
    Activations Density 0.026%

    No Known Activations