© 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. 34-GEMMASCOPE-RES-131K
    4. 103075
    Prev
    Next
    INDEX
    Explanations

    code inclusion directives

    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_34/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
    ऐ
    -0.75
    aneamente
    -0.75
    passport
    -0.73
     κάθε
    -0.71
    uestran
    -0.71
     disciplines
    -0.71
     χαρα
    -0.71
     ấy
    -0.70
     市場
    -0.69
     currencies
    -0.69
    POSITIVE LOGITS
     fiscale
    0.92
     region
    0.89
    tische
    0.80
    ꞌ
    0.80
     vial
    0.79
    <<<<<<<
    0.79
     ответы
    0.78
     nelle
    0.77
     +=
    0.77
     غزة
    0.76
    Activations Density 0.006%

    No Known Activations