© 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. 47879
    Prev
    Next
    INDEX
    Explanations

    chess board and results

    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
     যুবক
    0.51
    étion
    0.46
    wechsl
    0.45
    倬
    0.44
    ært
    0.44
     স্নাত
    0.44
    ভের
    0.44
    К
    0.44
    壯
    0.44
    𝐲
    0.44
    POSITIVE LOGITS
     depress
    0.41
     meios
    0.39
    ត្រ
    0.38
    /******/
    0.38
     biologist
    0.38
     DPP
    0.37
    ("#
    0.37
     haw
    0.37
    Бар
    0.37
     سمیت
    0.37
    Activations Density 0.014%

    No Known Activations