© 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. 31-GEMMASCOPE-2-RES-65K
    7. 9960
    Prev
    Next
    INDEX
    Explanations

    Physical Review Letters or scientific manuscripts

    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_65k_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
     جائے
    0.46
     decked
    0.46
    níku
    0.45
    ashire
    0.45
     ܡ
    0.45
     Đáp
    0.44
    дания
    0.43
     Wharf
    0.43
     وعد
    0.43
    起床
    0.43
    POSITIVE LOGITS
     nanow
    0.50
     supersymmetric
    0.45
     computational
    0.44
     manuscript
    0.44
    script
    0.43
    istisch
    0.43
    2
    0.43
     arxiv
    0.41
     Experiments
    0.41
     Heisenberg
    0.41
    Activations Density 0.002%

    No Known Activations