© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10585
    Prev
    Next
    INDEX
    Explanations

    code execution issues

    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
     yourself
    -1.48
     not
    -1.43
     dezelfde
    -1.30
    無く
    -1.24
     to
    -1.18
    ")
    -1.14
     menggunakan
    -1.11
     دارید
    -1.11
    quête
    -1.11
    鹛
    -1.10
    POSITIVE LOGITS
    lierung
    1.21
    ća
    1.11
     imparti
    1.10
     hears
    1.07
     („
    1.07
    راسیون
    1.05
    Ideally
    1.05
    詭
    1.02
    生まれる
    1.02
     HEAR
    1.02
    Activations Density 0.155%

    No Known Activations