© 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. 67963
    Prev
    Next
    INDEX
    Explanations

    legal decision dates

    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
    已经在
    -1.41
     våra
    -1.35
     мы
    -1.34
    depuis
    -1.30
     -,
    -1.30
    ,;
    -1.29
     lakini
    -1.28
     podemos
    -1.27
     jule
    -1.27
     '-',
    -1.27
    POSITIVE LOGITS
     each
    1.61
     Each
    1.45
     Př
    1.34
     각
    1.34
     obec
    1.34
     Vý
    1.33
    ющие
    1.32
     dismin
    1.30
     Finally
    1.30
     Unlike
    1.27
    Activations Density 0.012%

    No Known Activations