© 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. 16-GEMMASCOPE-2-RES-262K
    7. 110103
    Prev
    Next
    INDEX
    Explanations

    variable names and operators

    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_16_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
    ↵
    0.80
    us
    0.69
    W
    0.66
    ى
    0.65
    ında
    0.64
    J
    0.63
    IS
    0.61
    ए
    0.61
    :
    0.60
    V
    0.60
    POSITIVE LOGITS
    0.86
     is
    0.74
     a
    0.69
    、
    0.67
    ，“
    0.60
    ingar
    0.59
     preço
    0.57
     on
    0.56
     Pokémon
    0.56
    吗
    0.56
    Activations Density 0.038%

    No Known Activations