© 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. 15738
    Prev
    Next
    INDEX
    Explanations

    code imports and structure

    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
    ",{
    0.45
     Sudden
    0.41
     메모
    0.39
    ",$
    0.39
    jacke
    0.39
     muchísimo
    0.39
    "=>
    0.38
    /",
    0.38
    reathe
    0.38
    殮
    0.38
    POSITIVE LOGITS
    gathered
    0.39
    Sche
    0.38
    それを
    0.38
     swirl
    0.36
     bool
    0.36
    共
    0.35
    曽
    0.35
    [])
    0.35
    น้อย
    0.35
    Arg
    0.35
    Activations Density 0.021%

    No Known Activations