© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11202
    Prev
    Next
    INDEX
    Explanations

    door, openings, entrances

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

    literal and metaphorical doors

    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_40_width_16k_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
    મો
    0.41
     roofs
    0.40
     слоя
    0.39
    계를
    0.39
    ვნ
    0.38
    治理
    0.38
    繞
    0.38
     kru
    0.38
    船
    0.38
     Fasc
    0.38
    POSITIVE LOGITS
    🚪
    1.06
     Door
    0.92
     doors
    0.91
    Door
    0.91
     door
    0.90
    doors
    0.89
    ドア
    0.87
     Doors
    0.86
    door
    0.84
    Doors
    0.84
    Activations Density 0.167%

    No Known Activations