© 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. 100210
    Prev
    Next
    INDEX
    Explanations

    Tencent, DBS, ToDo, Gö, salivary

    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
    媄
    -2.67
     Einzelnen
    -2.59
     Hinblick
    -2.58
     Frühjahr
    -2.50
     Former
    -2.41
     получила
    -2.33
    諜
    -2.31
    錚
    -2.31
    acterísticas
    -2.25
     Allgemeinen
    -2.25
    POSITIVE LOGITS
    ’
    3.28
    `
    2.61
     ‚
    2.33
    硨
    2.27
    zed
    2.27
    Ꭳ
    2.27
     ocasion
    2.19
    埽
    2.17
     injust
    2.17
    あんまり
    2.14
    Activations Density 0.008%

    No Known Activations