© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10427
    Prev
    Next
    INDEX
    Explanations

    mass equivalence

    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_31_width_16k_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
     Afrique
    0.43
    >',
    0.42
     মতে
    0.40
     ຊ
    0.38
     Caterpillar
    0.38
    compressible
    0.38
     ጎ
    0.38
     முன்னோ
    0.38
     உருவாக்க
    0.37
    rolled
    0.37
    POSITIVE LOGITS
     länger
    0.41
     خاصيه
    0.38
     připoj
    0.38
    詃
    0.37
     stimmen
    0.36
    iban
    0.36
     longer
    0.36
    的人
    0.36
     Stel
    0.36
     সদ্য
    0.36
    Activations Density 0.015%

    No Known Activations