© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10943
    Prev
    Next
    INDEX
    Explanations

    rental or hire

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

    renting or borrowing

    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
    ুব্ধ
    0.39
     архитек
    0.38
     సాహిత్య
    0.38
    濺
    0.38
     сопро
    0.38
     இலக்கிய
    0.38
     verko
    0.38
     प्रोटीन
    0.37
     ගැ
    0.37
    protein
    0.37
    POSITIVE LOGITS
     rental
    2.52
     renting
    2.48
     rented
    2.45
     rentals
    2.38
     Rental
    2.33
    Rental
    2.28
    租
    2.25
    rental
    2.17
     rent
    2.08
    租赁
    2.06
    Activations Density 0.488%

    No Known Activations