© 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. 28988
    Prev
    Next
    INDEX
    Explanations

    PAD activity

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

    protein and enzyme abbreviations in scientific literature, particularly those ending with letters and sometimes numbers.

    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
    ambut
    -1.59
    )
    -1.40
    轳
    -1.25
     monasterio
    -1.24
    θρώ
    -1.23
    farmers
    -1.23
    閹
    -1.23
     amount
    -1.22
     ganzes
    -1.22
     you
    -1.20
    POSITIVE LOGITS
    “
    1.23
    5
    1.16
     menghadapi
    1.16
    ak
    1.15
    e
    1.12
    in
    1.11
    6
    1.10
    ct
    1.10
    illante
    1.09
     more
    1.07
    Activations Density 0.004%

    No Known Activations