© 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. 58779
    Prev
    Next
    INDEX
    Explanations

    business ownership and exit

    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
    Budget
    -1.04
    budget
    -1.04
     BUDGET
    -1.01
    さく
    -0.96
     бюджет
    -0.96
     budgetary
    -0.93
     bienfaits
    -0.93
     budget
    -0.92
    Mortgage
    -0.89
    ন
    -0.89
    POSITIVE LOGITS
     exit
    1.55
     succession
    1.46
     owner
    1.36
     owners
    1.34
     ownership
    1.28
     liquidity
    1.26
     founders
    1.26
    exit
    1.26
     Exit
    1.24
     exits
    1.23
    Activations Density 0.008%

    No Known Activations