© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 4308
    Prev
    Next
    INDEX
    Explanations

    range(n):

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     বিন
    0.38
    陇
    0.38
     या
    0.38
     Plantation
    0.37
    Vine
    0.37
    蒌
    0.37
    Ven
    0.36
    ายน
    0.36
    জ্জামান
    0.36
    ዦ
    0.36
    POSITIVE LOGITS
    ющи
    0.41
    лимп
    0.40
    いくつかの
    0.40
     estatal
    0.39
    GISL
    0.37
    descr
    0.36
     descriptive
    0.36
     estatales
    0.35
     state
    0.35
     descript
    0.35
    Activations Density 0.006%

    No Known Activations