© 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. 47676
    Prev
    Next
    INDEX
    Explanations

    Jackie names and antimicrobial terms

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

    names "Jackie" and terms related to antimicrobial properties.

    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
     \
    -3.30
     Selecting
    -3.05
     impetus
    -3.05
     Focusing
    -3.00
     Extending
    -2.94
    0
    -2.89
     ส์
    -2.84
     Personally
    -2.83
     requisite
    -2.80
     Identifying
    -2.77
    POSITIVE LOGITS
    ization
    3.47
    踽
    2.75
    </i>
    2.75
    fication
    2.70
    fares
    2.41
    孓
    2.39
     AMERIC
    2.38
    韪
    2.38
     tronic
    2.31
    ၟ
    2.30
    Activations Density 0.004%

    No Known Activations