© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 80817
    Prev
    Next
    INDEX
    Explanations

    voluntary disclosure or handling

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

    successfully delivered

    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_31_width_262k_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
     Okanagan
    0.47
     Ex
    0.44
     Aboriginal
    0.43
     A
    0.43
     Mas
    0.42
     Escherichia
    0.42
     Alkali
    0.42
     Exam
    0.42
     ABD
    0.42
     Uniti
    0.42
    POSITIVE LOGITS
    狀態
    0.48
    Ｒ
    0.48
    訓練
    0.47
     डीपी
    0.47
    EntryPoint
    0.47
    convén
    0.47
     ट्रेनिंग
    0.47
    पृथ
    0.47
    Trainer
    0.46
    空間
    0.46
    Activations Density 0.000%

    No Known Activations