© 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. 9895
    Prev
    Next
    INDEX
    Explanations

    names and acronyms like ELISA

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

    the name "Ella" and similar names like "Isabella", along with detecting "ELISA" as a laboratory test.

    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
    ):
    -2.50
    𝐲
    -2.47
    i
    -2.42
    c
    -2.33
    」
    -2.30
    恣
    -2.28
    糅
    -2.23
    踽
    -2.20
    ">
    -2.20
    蹉
    -2.11
    POSITIVE LOGITS
     cliquer
    2.58
    坶
    2.56
     verminder
    2.53
    壜
    2.41
    蟊
    2.41
    栊
    2.39
    ༵
    2.34
     beper
    2.34
     feront
    2.31
     voegen
    2.27
    Activations Density 0.003%

    No Known Activations