© 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. 14040
    Prev
    Next
    INDEX
    Explanations

    magazine charts

    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
     just
    -1.34
     kvinna
    -1.26
     it
    -1.26
    Ꮐ
    -1.24
    蕯
    -1.17
     bla
    -1.13
    czegóły
    -1.12
    所说
    -1.12
     sula
    -1.09
    \\
    -1.09
    POSITIVE LOGITS
     tři
    1.45
     téměř
    1.41
     ścian
    1.40
     systému
    1.38
    訁
    1.37
     člán
    1.36
     okolí
    1.36
     nový
    1.33
     любой
    1.32
     dobré
    1.30
    Activations Density 0.031%

    No Known Activations