© 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-65K
    7. 50527
    Prev
    Next
    INDEX
    Explanations

    words following commas

    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
     khususnya
    0.57
     terutama
    0.52
     especialmente
    0.52
    包括
    0.51
     особенно
    0.51
     особливо
    0.48
    它
    0.48
    특히
    0.48
    特に
    0.47
     خاصة
    0.47
    POSITIVE LOGITS
    ev
    0.42
     Hill
    0.39
    ander
    0.38
    ↵
    0.38
    ner
    0.38
    ätz
    0.38
    ale
    0.38
     Ev
    0.38
    eta
    0.37
     on
    0.37
    Activations Density 0.013%

    No Known Activations