© 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-16K
    7. 88
    Prev
    Next
    INDEX
    Explanations

    abstract qualities or systems

    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
    或者是
    0.39
     veya
    0.38
    或
    0.36
    或者
    0.35
     või
    0.35
     alebo
    0.34
     或
    0.33
    あるいは
    0.33
     ಅಥವಾ
    0.33
     ឬ
    0.31
    POSITIVE LOGITS
     without
    0.37
     galore
    0.37
     tanpa
    0.36
     ensures
    0.34
     effortlessly
    0.34
     সহজেই
    0.34
    的同时
    0.34
     senza
    0.33
     enhances
    0.33
     while
    0.33
    Activations Density 3.708%

    No Known Activations