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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48101
    Prev
    Next
    INDEX
    Explanations

    names of moths and brief explanations

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

    athletic and sporting achievements, particularly related to Olympic events and competitions.

    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_34/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
     Få
    -0.74
    appendTo
    -0.72
    rådet
    -0.72
    etre
    -0.71
     AVL
    -0.71
    🕊
    -0.69
    бус
    -0.69
     mainline
    -0.69
     bidder
    -0.69
    masi
    -0.67
    POSITIVE LOGITS
     pent
    1.11
     decathlon
    0.98
     Hep
    0.91
     Zin
    0.87
     score
    0.87
     Tet
    0.84
    🛁
    0.77
    pent
    0.77
     Renaissance
    0.76
     Pent
    0.75
    Activations Density 0.017%

    No Known Activations