© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 16715
    Prev
    Next
    INDEX
    Explanations

    practice and application

    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
     Bounty
    0.41
    ObjectTemp
    0.38
     Papers
    0.37
    不过
    0.37
     Cris
    0.37
    ທີ່
    0.37
    一个
    0.36
    的
    0.36
     Spur
    0.35
    ['
    0.35
    POSITIVE LOGITS
     cognitiva
    0.44
    <unused311>
    0.44
    <unused635>
    0.43
    <unused612>
    0.42
     simonsen
    0.41
     pembelajaran
    0.41
     caracteriza
    0.41
     identifik
    0.41
    creational
    0.41
    휋
    0.40
    Activations Density 0.004%

    No Known Activations