© 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. 14006
    Prev
    Next
    INDEX
    Explanations

    medical context and related conditions

    np_acts-logits-general · gemini-2.5-flash-lite

    conceptual explanations and informational text about systems, conditions, or processes.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     særlig
    -1.57
     различни
    -1.54
     разных
    -1.51
     мужская
    -1.40
     всичко
    -1.39
     всеки
    -1.38
     trucos
    -1.38
     считается
    -1.38
     apuestas
    -1.37
     всички
    -1.36
    POSITIVE LOGITS
     our
    1.98
     we
    1.60
     Antik
    1.48
     μας
    1.38
    руем
    1.37
     рекомен
    1.35
     unseren
    1.34
     бампер
    1.31
    我们
    1.31
    ATIVO
    1.28
    Activations Density 0.027%

    No Known Activations