© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116332
    Prev
    Next
    INDEX
    Explanations

    programming errors and technical terms

    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
    madeus
    -0.95
     услыша
    -0.95
    ⿺
    -0.94
     ambil
    -0.91
     élastique
    -0.90
    eronau
    -0.88
    гка
    -0.86
    状况
    -0.86
    senic
    -0.86
     suhu
    -0.85
    POSITIVE LOGITS
    0
    1.36
    log
    0.98
    1
    0.92
     Cardiff
    0.90
    ύ
    0.88
     Chennai
    0.88
    ia
    0.87
     услуги
    0.86
     сде
    0.85
    那就是
    0.85
    Activations Density 0.112%

    No Known Activations