© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2512
    Prev
    Next
    INDEX
    Explanations

    table structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
     fingerprints
    0.79
     suffix
    0.69
    ˝
    0.67
    場合がございます
    0.66
    otification
    0.66
     monographs
    0.65
     followed
    0.65
     parietal
    0.65
    ΰ
    0.65
     prerogative
    0.64
    POSITIVE LOGITS
     table
    1.69
    table
    1.67
    Table
    1.65
     Table
    1.57
    tabular
    1.52
    表格
    1.51
     tabel
    1.45
    <table>
    1.44
     tabular
    1.43
     tabella
    1.40
    Activations Density 0.295%

    No Known Activations