© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13855
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

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

    what they do

    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_16k_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
    ↵↵
    0.56
    9
    0.53
    ↵↵↵
    0.51
    7
    0.51
    6
    0.49
    8
    0.47
    4
    0.47
    5
    0.47
    had
    0.46
     Elf
    0.46
    POSITIVE LOGITS
    |।
    0.57
    лакти
    0.53
     território
    0.52
     seco
    0.50
    Ꮨ
    0.50
     tierras
    0.49
     terão
    0.48
     mentoring
    0.47
     корректи
    0.47
     домой
    0.47
    Activations Density 0.001%

    No Known Activations