© 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. 9338
    Prev
    Next
    INDEX
    Explanations

    parks and hiking

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

    hiking, parks, picnics

    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
     ആരോപ
    0.50
     defam
    0.50
     compradores
    0.50
     comprador
    0.50
     చర్చ
    0.49
     ಆತ್ಮ
    0.49
    齑
    0.48
    臨床
    0.47
     isomorphic
    0.46
     supremacy
    0.45
    POSITIVE LOGITS
     park
    1.05
     Hiking
    1.05
    公园
    0.98
     hiking
    0.96
     Hike
    0.94
     Parks
    0.94
     campground
    0.94
     hikers
    0.93
     parks
    0.93
    Hiking
    0.91
    Activations Density 0.279%

    No Known Activations