© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6058
    Prev
    Next
    INDEX
    Explanations

    positive descriptors of travel or places

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

    travel plan section titles

    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_53_width_65k_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
    我会
    0.47
     मुझसे
    0.47
    我在
    0.46
    我家
    0.46
     /ˈ
    0.44
    が存在
    0.44
     нередко
    0.44
    '=>'
    0.44
    我已经
    0.43
     मैंने
    0.43
    POSITIVE LOGITS
     AMAZING
    0.65
     different
    0.64
     incredible
    0.63
     amazing
    0.61
     невероят
    0.61
     HUGE
    0.60
    different
    0.57
     increíble
    0.57
     разных
    0.56
     diferentes
    0.56
    Activations Density 0.100%

    No Known Activations