© 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. 68091
    Prev
    Next
    INDEX
    Explanations

    common structures and proper nouns

    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
     each
    -1.07
    同士
    -1.07
     similaire
    -1.06
     guaranty
    -1.05
     rédig
    -1.05
    -
    -1.04
     exactement
    -1.03
    ैक
    -1.02
    すっ
    -1.02
     beispielsweise
    -0.99
    POSITIVE LOGITS
     esqueleto
    1.40
    пустить
    1.22
    」、「
    1.16
    ต้อง
    1.16
    包括
    1.16
    ⏟
    1.15
    他们
    1.14
    今回は
    1.13
    现在
    1.13
    我们
    1.13
    Activations Density 0.054%

    No Known Activations