© 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. 110761
    Prev
    Next
    INDEX
    Explanations

    organization ownership 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
    errHandler
    -0.98
    äter
    -0.89
    óval
    -0.87
     Refinery
    -0.86
    ender
    -0.85
    ধ
    -0.83
     Recipients
    -0.82
     Handler
    -0.82
    ITABLE
    -0.82
    ichord
    -0.81
    POSITIVE LOGITS
     owners
    1.34
     owner
    1.11
     managers
    1.11
    goers
    1.11
     operator
    1.06
     size
    1.05
     closures
    1.03
     operators
    1.00
     CEOs
    0.97
     management
    0.96
    Activations Density 0.088%

    No Known Activations