© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14089
    Prev
    Next
    INDEX
    Explanations

    `where` followed by definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    ）、
    0.66
    들에게
    0.64
    한테
    0.62
    )、
    0.61
     Certains
    0.61
    》、《
    0.59
    ﻬ
    0.59
     Ceux
    0.57
     Pixar
    0.56
     ਮ
    0.55
    POSITIVE LOGITS
    which
    0.96
     which
    0.95
     where
    0.83
    $.
    0.82
    where
    0.78
    .
    0.76
     whereby
    0.74
     owing
    0.73
    %.
    0.72
     wobei
    0.72
    Activations Density 0.128%

    No Known Activations