© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86329
    Prev
    Next
    INDEX
    Explanations

    genome editing

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

    technical and scientific terms or acronyms, particularly related to technology, biology, or organizational entities.

    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
     it
    -1.70
     their
    -1.42
     these
    -1.41
     you
    -1.39
     These
    -1.35
     two
    -1.30
     sepeda
    -1.24
     hänen
    -1.23
     both
    -1.23
     eeuw
    -1.22
    POSITIVE LOGITS
    gliere
    1.38
    Více
    1.38
     "@/
    1.30
    zdroj
    1.30
    紲
    1.29
    Zdroj
    1.27
    renowned
    1.27
     ビュー
    1.26
    Tento
    1.26
     وذلك
    1.23
    Activations Density 0.113%

    No Known Activations