© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1939
    Prev
    Next
    INDEX
    Explanations

    assignment, operation, or sequence

    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_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
    יל
    0.38
     традиции
    0.35
    唵
    0.35
    ศาส
    0.34
    expérience
    0.34
    ujourd
    0.33
     вакци
    0.33
    attiyam
    0.33
    हमारी
    0.33
    <unused2039>
    0.33
    POSITIVE LOGITS
     desired
    0.38
     desirable
    0.38
     immediately
    0.37
     distinct
    0.36
     subsequent
    0.36
    ,
    0.35
     likely
    0.35
     automatically
    0.34
    ↵
    0.32
     d
    0.32
    Activations Density 2.375%

    No Known Activations