© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11352
    Prev
    Next
    INDEX
    Explanations

    GBM patients, bone marrow, betamethasone

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

    medical and scientific abbreviations, particularly "BM" and related terms in academic 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_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
    s
    -8.81
    ی
    -4.13
    ים
    -3.55
    的
    -3.23
    ς
    -2.81
    та
    -2.70
     ladri
    -2.67
    ’
    -2.63
    üşonlu
    -2.61
    alamualaikum
    -2.56
    POSITIVE LOGITS
     We
    2.58
    𐄁
    2.58
     Roughly
    2.55
    くらいの
    2.53
     وم
    2.48
     Increases
    2.45
     lessening
    2.42
     Subsequently
    2.41
     penjelasan
    2.39
     mouseClicked
    2.34
    Activations Density 0.047%

    No Known Activations