© 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. 74164
    Prev
    Next
    INDEX
    Explanations

    technical code and jargon

    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
    呖
    -2.72
    蔸
    -2.61
     oleh
    -2.47
    ſtra
    -2.42
    秝
    -2.41
    聍
    -2.33
    汭
    -2.27
     碗
    -2.17
     طف
    -2.14
    .
    -2.14
    POSITIVE LOGITS
    ні
    2.77
     Есть
    2.69
    ’
    2.47
     Reaching
    2.47
     There
    2.44
     Discovering
    2.39
     configuring
    2.36
     Allowing
    2.30
     Ensuring
    2.22
     Physically
    2.22
    Activations Density 0.002%

    No Known Activations