© 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. 48627
    Prev
    Next
    INDEX
    Explanations

    rebound weight gain

    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
    ر
    0.46
    دا
    0.45
    ص
    0.44
    یمپ
    0.43
    T
    0.43
    ت
    0.42
    Ш
    0.41
    专业
    0.41
    Пре
    0.41
    Ҳ
    0.41
    POSITIVE LOGITS
    блица
    0.45
    ghis
    0.42
     cardNumber
    0.42
     https
    0.41
     http
    0.41
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.41
    ೆಯೇ
    0.41
     nodemailer
    0.41
    ✞
    0.41
    
    0.40
    Activations Density 0.001%

    No Known Activations