© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 251119
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
    tanh
    0.52
    ἦ
    0.52
    त्तों
    0.50
    鄴
    0.50
    ಾದ
    0.46
    IDADES
    0.45
    उदाहरण
    0.45
    兩
    0.44
    ার্স
    0.44
     Syk
    0.43
    POSITIVE LOGITS
    -
    0.51
     ინტერ
    0.47
     Bupati
    0.46
     대상
    0.45
     ढंग
    0.42
     Whisper
    0.42
     ต้อง
    0.42
     ।*
    0.42
     Powder
    0.41
     Contact
    0.41
    Activations Density 0.002%

    No Known Activations