© 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. 73100
    Prev
    Next
    INDEX
    Explanations

    email subjects with colons

    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
     you
    -1.70
     เป็น
    -1.65
    を利用
    -1.57
    泚
    -1.52
    </h3>
    -1.51
     příjem
    -1.38
     vás
    -1.38
    dsquared
    -1.35
     znám
    -1.34
    kres
    -1.34
    POSITIVE LOGITS
     Хотя
    1.57
     iniqu
    1.54
     beholder
    1.44
    圜
    1.40
     indestru
    1.38
     ayat
    1.37
    Transk
    1.35
     sobri
    1.35
    謾
    1.34
    Détails
    1.31
    Activations Density 0.001%

    No Known Activations