© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11879
    Prev
    Next
    INDEX
    Explanations

    court clerk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     why
    -1.20
    tifies
    -1.13
    رفة
    -1.12
     fazem
    -1.10
     we
    -1.09
     estratégica
    -1.09
    bluza
    -1.07
    s
    -1.07
    妣
    -1.06
     have
    -1.05
    POSITIVE LOGITS
    lceil
    1.28
    렷
    1.21
    ˖
    1.20
    ordano
    1.18
    )^{
    1.16
    ranslated
    1.15
    rekt
    1.12
    LEBR
    1.11
     任务
    1.11
    anow
    1.08
    Activations Density 0.019%

    No Known Activations