© 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. 1422
    Prev
    Next
    INDEX
    Explanations

    biological and anatomical suffixes

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

    medical and biological terminology related to anatomical structures and tissues.

    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
    　　-
    -1.98
    ⇣
    -1.91
    　　*
    -1.89
    ！"
    -1.87
    具体的
    -1.84
    ♪♪
    -1.78
    ～～～～
    -1.77
    ggiare
    -1.75
    umumkan
    -1.71
    ཫ
    -1.70
    POSITIVE LOGITS
     The
    2.27
    ’
    2.09
     A
    1.85
     He
    1.81
     When
    1.77
     irse
    1.73
     WAY
    1.66
     THE
    1.66
     OF
    1.64
    </b>
    1.63
    Activations Density 0.972%

    No Known Activations