© 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. 104991
    Prev
    Next
    INDEX
    Explanations

    baby, recall, known, books, stars

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

    geographic locations

    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
    Storage
    0.48
     كيفية
    0.47
    Whenever
    0.43
     مواد
    0.42
    이며
    0.40
    Tile
    0.40
    fels
    0.40
    钰
    0.39
    ForItem
    0.39
     منجر
    0.39
    POSITIVE LOGITS
     Москве
    0.55
     Moscow
    0.52
     അമേ
    0.49
     internacional
    0.49
     Vancouver
    0.48
     đang
    0.48
     Stockholm
    0.48
     সোভ
    0.48
    𝗶
    0.48
    𝑎
    0.48
    Activations Density 0.001%

    No Known Activations