© 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. 4089
    Prev
    Next
    INDEX
    Explanations

    explaining concepts and providing descriptions

    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
    container
    0.47
    form
    0.45
    fin
    0.41
    d
    0.40
    list
    0.39
    الد
    0.39
    ด
    0.39
    Container
    0.38
    javax
    0.38
    त
    0.38
    POSITIVE LOGITS
     ง่าย
    0.48
    <unused983>
    0.47
     кількість
    0.45
     SoaException
    0.45
     reunião
    0.45
     მნიშვნელ
    0.45
    <unused2112>
    0.45
    <unused984>
    0.43
     rospy
    0.42
    <unused716>
    0.41
    Activations Density 0.152%

    No Known Activations