© 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. 10-GEMMASCOPE-RES-131K
    7. 43854
    Prev
    Next
    INDEX
    Explanations

    CUDA toolkit or Caspian Sea

    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_10/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
     gustado
    -2.27
    葑
    -2.03
    大学の
    -1.98
     encantado
    -1.98
    secta
    -1.98
    珝
    -1.96
    祘
    -1.95
    栝
    -1.87
    螃蟹
    -1.85
    マリー
    -1.85
    POSITIVE LOGITS
     folos
    2.47
    ,“
    2.33
     但
    2.28
    3
    2.27
    ه
    2.22
    1
    2.20
     einzigartige
    2.17
     fiecare
    2.17
     deoarece
    2.16
     prossima
    2.11
    Activations Density 0.008%

    No Known Activations