© 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. 22371
    Prev
    Next
    INDEX
    Explanations

    United States District Court East District

    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
    <bos>
    -1.74
    いわゆる
    -1.44
     който
    -1.39
     your
    -1.38
    したいと思います
    -1.32
    ائه
    -1.32
     всеки
    -1.31
     který
    -1.28
    发布于
    -1.27
     joindre
    -1.27
    POSITIVE LOGITS
     celebró
    1.45
     they
    1.44
    逦
    1.43
     East
    1.41
     \%(
    1.41
     immedi
    1.39
     astu
    1.38
     Coupé
    1.37
     cauſe
    1.32
     doesn
    1.31
    Activations Density 0.054%

    No Known Activations