© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 614
    Prev
    Next
    INDEX
    Explanations

    newline and line breaks

    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
     that
    -2.16
    ᠂
    -1.61
     say
    -1.61
     damaligen
    -1.58
    ‌هایی
    -1.52
     each
    -1.44
     Unii
    -1.43
     those
    -1.41
     jeweiligen
    -1.40
    }
    -1.40
    POSITIVE LOGITS
     menyen
    1.64
     kazak
    1.45
    僅
    1.45
    ！"
    1.43
     etek
    1.41
     diki
    1.37
    莇
    1.37
    undan
    1.37
     違い
    1.34
     rosse
    1.34
    Activations Density 0.004%

    No Known Activations