© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107943
    Prev
    Next
    INDEX
    Explanations

    land of opportunity

    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
     city
    -0.85
     locality
    -0.77
     City
    -0.75
     komment
    -0.74
     Notes
    -0.74
    掂
    -0.71
    lands
    -0.71
    ⓸
    -0.70
     Kyoto
    -0.69
     земли
    -0.68
    POSITIVE LOGITS
     enchantment
    1.00
     OPPORTUNITY
    0.95
     dreams
    0.95
     opportunities
    0.94
     milk
    0.91
    opportunity
    0.90
     contrasts
    0.89
     opportunity
    0.88
     oportunidades
    0.88
     promise
    0.88
    Activations Density 0.028%

    No Known Activations