© 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. 44113
    Prev
    Next
    INDEX
    Explanations

    Western blot and immunoassays

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

    scientific terminology related to laboratory techniques and biological assays, particularly immunological methods like Western blots and serum testing.

    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
     would
    -1.76
    =
    -1.48
     is
    -1.38
     his
    -1.24
     onStart
    -1.23
     number
    -1.23
    ('
    -1.19
    饪
    -1.16
     incluso
    -1.13
    -1.13
    POSITIVE LOGITS
     खोज
    1.25
    жі
    1.23
    ⅜
    1.23
    dí
    1.20
    handlung
    1.19
     rewind
    1.15
     Chaplain
    1.13
    setColumns
    1.13
    illante
    1.13
     expla
    1.13
    Activations Density 0.122%

    No Known Activations