© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4296
    Prev
    Next
    INDEX
    Explanations

    weight loss

    np_acts-logits-general · gemini-2.5-flash-lite

    loss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    酛
    0.39
    FileAlignment
    0.35
    ന്തി
    0.35
     छापा
    0.34
     glfw
    0.34
    ဒီ
    0.33
    繁
    0.32
    ))=\
    0.32
     اجازت
    0.32
    nment
    0.32
    POSITIVE LOGITS
     loss
    4.22
     lost
    4.06
    Loss
    4.06
     Loss
    4.03
    loss
    3.98
     втра
    3.94
     lose
    3.92
     losing
    3.89
     LOSS
    3.88
     loses
    3.86
    Activations Density 0.533%

    No Known Activations