© 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. 68323
    Prev
    Next
    INDEX
    Explanations

    tachy and brady variants

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

    medical terminology related to cardiac rhythms and biological classifications, particularly words containing "tachy" and "brady" prefixes.

    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
     Which
    -2.78
     WHICH
    -2.73
     she
    -2.30
    ῞
    -2.28
    哢
    -2.27
    }$.
    -2.23
    OUTUBE
    -2.20
     comprised
    -2.17
    퐸
    -2.16
     situated
    -2.14
    POSITIVE LOGITS
    3
    2.41
    begin
    2.30
    </td>
    2.11
    𓍊
    2.09
    =
    2.05
    鋨
    2.03
    \
    1.97
    ઁ
    1.97
     влияет
    1.95
    一个
    1.95
    Activations Density 0.013%

    No Known Activations