© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 22424
    Prev
    Next
    INDEX
    Explanations

    tropical nature and rooms

    np_acts-logits-general · gemini-2.5-flash-lite

    tropical beach destinations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    札幌
    0.48
    地铁
    0.48
     लंदन
    0.47
     Budapest
    0.46
     subway
    0.46
     München
    0.46
     जम्मू
    0.45
    🚇
    0.45
     महानगर
    0.45
     Vienna
    0.43
    POSITIVE LOGITS
     Tropical
    0.96
     mangroves
    0.95
     mangrove
    0.94
     tropical
    0.93
    🌴
    0.91
     coconut
    0.90
     Coconut
    0.87
    Tropical
    0.87
    tropical
    0.83
     coral
    0.81
    Activations Density 0.127%

    No Known Activations