© 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. 22-GEMMASCOPE-RES-131K
    7. 16124
    Prev
    Next
    INDEX
    Explanations

    immunohistochemistry and immunoreactivity

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

    scientific terms related to immunohistochemistry and cellular staining techniques in research papers.

    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_22/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
     case
    -1.20
     taşlı
    -1.18
    了些
    -1.16
     baskılı
    -1.15
    ivir
    -1.14
     entraîner
    -1.13
     读取
    -1.12
     计算
    -1.11
     السياس
    -1.11
    circled
    -1.11
    POSITIVE LOGITS
     on
    1.13
     showed
    1.08
     preen
    1.08
    ılığı
    1.08
    Tekst
    1.02
    قاط
    1.01
     confirms
    0.99
     showing
    0.96
    //<
    0.96
    Legende
    0.95
    Activations Density 0.190%

    No Known Activations