© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9602
    Prev
    Next
    INDEX
    Explanations

    DPS, Meredith, Elle, Tess

    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
     Frequently
    -3.22
     Luckily
    -2.98
     Roughly
    -2.88
     Acuerdo
    -2.73
     Fortunately
    -2.64
     Officially
    -2.64
     Specifically
    -2.59
     Seriously
    -2.53
     Already
    -2.52
     Possibly
    -2.48
    POSITIVE LOGITS
    栊
    2.77
     heath
    2.75
    ！"
    2.64
    那我
    2.53
    itemBuilder
    2.50
     необходи
    2.47
    ных
    2.44
    N
    2.39
    錞
    2.38
     ihe
    2.33
    Activations Density 0.015%

    No Known Activations