© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77492
    Prev
    Next
    INDEX
    Explanations

    optimism hope confidence

    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
     sfera
    -1.00
     HON
    -0.85
    uſ
    -0.84
     Kuan
    -0.82
     ながら
    -0.81
    wertes
    -0.81
    🐈
    -0.80
    
    -0.80
    ________,
    -0.79
     menegaskan
    -0.78
    POSITIVE LOGITS
     optimistic
    4.41
     optimism
    4.38
    optimis
    3.27
     hopeful
    3.09
     Optimis
    3.06
    Optimis
    3.02
     optimis
    2.83
     confident
    2.81
     confidence
    2.78
     hope
    2.56
    Activations Density 0.054%

    No Known Activations