© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 3568
    Prev
    Next
    INDEX
    Explanations

    offering help or options

    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
     إذا
    0.39
     nếu
    0.32
     jeżeli
    0.32
     اگر
    0.31
     dacă
    0.31
    Якщо
    0.30
     وقتی
    0.29
    。
    0.29
    如果在
    0.29
     якщо
    0.29
    POSITIVE LOGITS
     he
    0.31
     उसे
    0.30
     she
    0.30
     it
    0.30
     they
    0.29
     તેણે
    0.29
    または
    0.29
     or
    0.28
     hän
    0.28
    at
    0.27
    Activations Density 0.104%

    No Known Activations