© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104940
    Prev
    Next
    INDEX
    Explanations

    regulatory factors and molecules

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

    proteins and biochemical molecules in scientific text.

    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
    鳎
    -1.60
    癶
    -1.59
     Einfluß
    -1.58
     Schluß
    -1.57
    阏
    -1.54
     réserver
    -1.52
    ⁛
    -1.51
    ︲
    -1.50
    ㉒
    -1.48
    褙
    -1.47
    POSITIVE LOGITS
     is
    2.02
     in
    1.89
     Dezember
    1.52
     Februar
    1.39
     at
    1.38
     for
    1.30
     should
    1.27
     поэтому
    1.27
     very
    1.23
     G
    1.22
    Activations Density 1.098%

    No Known Activations