© 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-16K
    7. 2535
    Prev
    Next
    INDEX
    Explanations

    then, after, indexed

    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
    אם
    0.44
     создавать
    0.44
     coronation
    0.43
    わり
    0.43
     இ
    0.41
     развитии
    0.41
     criar
    0.40
    忶
    0.39
    愆
    0.39
     ख
    0.39
    POSITIVE LOGITS
     then
    0.79
     سپس
    0.77
    然后
    0.75
     następnie
    0.71
    然後
    0.70
     потім
    0.68
     anschließend
    0.67
     rồi
    0.66
     THEN
    0.66
     затем
    0.65
    Activations Density 0.688%

    No Known Activations