© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11249
    Prev
    Next
    INDEX
    Explanations

    code snippets and commands

    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_22/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
    raire
    -0.86
     فقط
    -0.86
     объяс
    -0.86
     only
    -0.85
     deines
    -0.82
    //...
    -0.82
    områ
    -0.81
     seulement
    -0.79
    ="<?=$
    -0.79
    ricos
    -0.79
    POSITIVE LOGITS
    sety
    1.04
    iligten
    1.00
     redus
    0.95
    kann
    0.90
    роб
    0.89
    콘
    0.88
    OfBirth
    0.88
    ništvo
    0.87
    quartered
    0.85
    veden
    0.85
    Activations Density 0.001%

    No Known Activations