© 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. 10-GEMMASCOPE-RES-131K
    7. 48070
    Prev
    Next
    INDEX
    Explanations

    high-throughput methods

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

    technical terminology related to high-throughput data processing in scientific research.

    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_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
     if
    -1.35
    ordning
    -1.33
    initState
    -1.31
    赑
    -1.26
     pokud
    -1.23
    した後
    -1.23
     planea
    -1.20
     jeśli
    -1.20
    ⍝
    -1.20
     यदि
    -1.15
    POSITIVE LOGITS
    </strong>
    1.48
    </b>
    1.47
     yako
    1.38
    異なります
    1.20
     interessi
    1.20
     réessayer
    1.20
     pamoja
    1.17
    kowej
    1.16
     yetu
    1.15
    azah
    1.12
    Activations Density 0.326%

    No Known Activations