© 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. 13854
    Prev
    Next
    INDEX
    Explanations

    paste here

    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
    齎
    0.69
    ۰
    0.64
     sired
    0.62
     spez
    0.61
     thúc
    0.60
     cadáver
    0.60
    is
    0.59
     dív
    0.59
    큐
    0.59
     desses
    0.59
    POSITIVE LOGITS
     in
    1.09
    在
    0.84
    на
    0.81
    abouts
    0.77
    ifrån
    0.76
    ใน
    0.71
     i
    0.64
    ال
    0.64
     মূলত
    0.63
    aj
    0.61
    Activations Density 0.083%

    No Known Activations