© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 80020
    Prev
    Next
    INDEX
    Explanations

    code definitions

    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
     چیه
    -1.10
    тин
    -1.00
    тное
    -0.93
    urants
    -0.91
    unless
    -0.88
     Funcion
    -0.87
    prisingly
    -0.87
     ApiClient
    -0.86
    温泉
    -0.85
    ⬎
    -0.85
    POSITIVE LOGITS
     iprot
    0.94
     pietra
    0.88
     seguía
    0.83
    iarkan
    0.81
    users
    0.81
    백
    0.79
    นะนำ
    0.78
     kän
    0.77
     known
    0.77
     sợi
    0.77
    Activations Density 0.002%

    No Known Activations