© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128758
    Prev
    Next
    INDEX
    Explanations

    quarantine, quarters, ransom, triage, fever

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

    terms related to quarantine, isolation, and confinement.

    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
    ле
    -2.33
    人们
    -2.19
    </i>
    -2.17
     sarà
    -2.16
     Erinnerungen
    -2.14
     partecipanti
    -2.14
     accompanying
    -2.13
     spannend
    -2.11
     gelieb
    -2.11
     Of
    -2.11
    POSITIVE LOGITS
    e
    2.58
    ↵
    2.58
    哔
    2.31
    निक
    2.28
    ?
    2.17
    媗
    2.17
    tocks
    2.11
    愎
    2.09
    taker
    2.05
     sowohl
    2.03
    Activations Density 0.002%

    No Known Activations