© 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. 75686
    Prev
    Next
    INDEX
    Explanations

    professional career information

    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
     befür
    -0.87
    されていない
    -0.82
     about
    -0.82
     easy
    -0.81
     people
    -0.80
     if
    -0.80
    kaitan
    -0.79
     where
    -0.78
    bigli
    -0.77
     it
    -0.76
    POSITIVE LOGITS
    FIGHT
    0.98
     professionnels
    0.89
    ან
    0.87
     drawdown
    0.86
     профессиона
    0.85
    professional
    0.85
     exorbit
    0.84
     échanti
    0.83
     career
    0.82
    thys
    0.82
    Activations Density 0.016%

    No Known Activations