© 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. 54357
    Prev
    Next
    INDEX
    Explanations

    descriptions, historical periods, numerical sequences

    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
     உயர
    0.51
    區域
    0.50
    珴
    0.48
    地區
    0.47
     জানতে
    0.45
     sajana
    0.45
    ︰
    0.45
    㘟
    0.44
     rekom
    0.44
     മഹാ
    0.44
    POSITIVE LOGITS
     BART
    0.44
     zip
    0.41
     stuff
    0.40
     T
    0.39
    lijk
    0.39
    нул
    0.39
     lien
    0.38
     noct
    0.38
     [
    0.38
     Smok
    0.38
    Activations Density 0.001%

    No Known Activations