© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 513
    Prev
    Next
    INDEX
    Explanations

    explaining structured concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-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
    which
    0.39
    MYSQL
    0.29
    Which
    0.29
     which
    0.28
    Known
    0.28
    }{
    0.28
    allows
    0.28
     \
    0.28
     "\
    0.28
     sogenannten
    0.28
    POSITIVE LOGITS
     funcionando
    0.71
     being
    0.69
     coming
    0.65
     underway
    0.64
     lurking
    0.63
     taking
    0.61
     sendo
    0.61
     trabajando
    0.61
     vying
    0.61
     creciendo
    0.60
    Activations Density 2.979%

    No Known Activations