© 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. 34-GEMMASCOPE-RES-131K
    7. 117148
    Prev
    Next
    INDEX
    Explanations

    CRISPR gene editing

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

    CRISPR-Cas9 gene editing technology and related genetic modification terms.

    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_34/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
     таком
    -0.77
     ||
    -0.70
     wrapped
    -0.68
     absorption
    -0.68
     environmental
    -0.67
    発信
    -0.67
     strengthening
    -0.66
    インタ
    -0.66
    oter
    -0.66
    INTER
    -0.66
    POSITIVE LOGITS
     CRISPR
    1.58
     editing
    1.48
    Editing
    1.31
     TAL
    1.27
     edits
    1.27
    Edit
    1.25
     Editing
    1.23
    editing
    1.23
     edit
    1.21
    Cas
    1.17
    Activations Density 0.055%

    No Known Activations