© 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-16K
    7. 3242
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and matrices

    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_16k_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
     indul
    0.48
     supermarkets
    0.47
    浃
    0.44
    बारक
    0.43
    forecast
    0.43
     forecast
    0.42
     amost
    0.42
     daftar
    0.42
     garn
    0.42
     suitcases
    0.42
    POSITIVE LOGITS
    Matrix
    0.46
    Eigen
    0.45
    Bone
    0.44
    Block
    0.43
     matrix
    0.42
    Chromosome
    0.42
    ผ
    0.42
    Spectrum
    0.41
    Const
    0.41
    Fundamental
    0.41
    Activations Density 0.023%

    No Known Activations