Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12406
    Prev
    Next
    INDEX
    Explanations

    numbers with asterisks

    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
    isotropic
    0.36
    Parameter
    0.35
     initialize
    0.35
    {}
    0.35
    ==
    0.34
     list
    0.33
     device
    0.33
    parameter
    0.33
     apparence
    0.33
     Initialize
    0.32
    POSITIVE LOGITS
     Deacon
    0.32
     شاهد
    0.30
    дек
    0.30
     талант
    0.30
    훈
    0.30
     Приступљено
    0.30
     соци
    0.29
     fortalecer
    0.29
     súper
    0.29
     مقام
    0.29
    Activations Density 0.001%

    No Known Activations