© 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. 23315
    Prev
    Next
    INDEX
    Explanations

    spatial design for residential development

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

    urban design and accessibility

    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
    毀
    0.66
     недавно
    0.64
    毁
    0.63
    诋
    0.63
    ómago
    0.59
    decine
    0.58
    损坏
    0.57
    古い
    0.57
    毁灭
    0.57
    叕
    0.56
    POSITIVE LOGITS
     walkable
    0.83
     design
    0.80
     Design
    0.76
     spatial
    0.71
     spatially
    0.71
     balconies
    0.68
     Space
    0.67
     walkways
    0.67
     proposed
    0.65
     interface
    0.65
    Activations Density 0.136%

    No Known Activations