© 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. 62694
    Prev
    Next
    INDEX
    Explanations

    locations and geographical regions

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

    lists of services topics technologies

    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
     ideia
    0.39
    付ける
    0.39
    Good
    0.39
    投稿
    0.38
    Giá
    0.38
     isEmpty
    0.38
    进
    0.37
    信用
    0.37
    记录
    0.36
    顼
    0.36
    POSITIVE LOGITS
     pharmacies
    0.41
     كأس
    0.39
     phospholipids
    0.39
    saxophone
    0.37
    NYSE
    0.37
    ដែលអាច
    0.37
     carbohydrates
    0.37
     வன
    0.37
     seamen
    0.37
     monasteries
    0.36
    Activations Density 0.041%

    No Known Activations