© 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. 58502
    Prev
    Next
    INDEX
    Explanations

    smart devices

    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
    ↵
    -2.42
    狁
    -1.67
     polski
    -1.55
    蜮
    -1.51
    нии
    -1.45
    ranean
    -1.44
     echte
    -1.43
     spannend
    -1.42
     tidligere
    -1.41
     obviamente
    -1.41
    POSITIVE LOGITS
     вашу
    1.63
    this
    1.59
     become
    1.52
     笔
    1.50
     finds
    1.48
    x
    1.45
     pratica
    1.43
     cannot
    1.43
     veta
    1.41
     out
    1.40
    Activations Density 0.024%

    No Known Activations