© 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. 86218
    Prev
    Next
    INDEX
    Explanations

    object keys in code

    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
    ‌ها
    -1.56
     podremos
    -1.53
    屣
    -1.48
    自然是
    -1.45
    żeli
    -1.41
    adita
    -1.40
    뜩
    -1.38
    ються
    -1.38
    蔑
    -1.38
     négy
    -1.37
    POSITIVE LOGITS
     that
    2.28
     sehingga
    1.82
    بري
    1.67
    慙
    1.52
     using
    1.44
     stav
    1.39
     所以
    1.38
    B
    1.38
    がありません
    1.38
    K
    1.37
    Activations Density 0.031%

    No Known Activations