© 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-65K
    7. 15847
    Prev
    Next
    INDEX
    Explanations

    data and datasets

    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
    ë
    0.43
    ð
    0.41
    Jeh
    0.40
    iritual
    0.40
     തോന്ന
    0.40
     останавли
    0.40
    ремен
    0.40
     Jehovah
    0.39
     bebidas
    0.39
    愜
    0.39
    POSITIVE LOGITS
     datasets
    0.99
     dataset
    0.97
     Dataset
    0.89
    dataset
    0.84
    Dataset
    0.78
    数据集
    0.78
    datasets
    0.77
     samples
    0.76
     데이터를
    0.71
    Datasets
    0.71
    Activations Density 0.397%

    No Known Activations