© 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. 22-GEMMASCOPE-RES-131K
    7. 14312
    Prev
    Next
    INDEX
    Explanations

    deep

    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
     There
    -1.05
    文件中
    -1.03
     volgens
    -1.00
    嵛
    -1.00
     there
    -0.98
     compartido
    -0.96
     sumamente
    -0.96
     eficacia
    -0.96
     apropiado
    -0.96
    ｐ
    -0.96
    POSITIVE LOGITS
    <bos>
    1.46
    很有
    1.04
    甚至
    0.99
    
    0.90
    \
    0.86
     comentários
    0.85
    只
    0.85
     fama
    0.84
    5
    0.84
    确实
    0.82
    Activations Density 0.100%

    No Known Activations