© 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. 34-GEMMASCOPE-RES-131K
    4. 80996
    Prev
    Next
    INDEX
    Explanations

    genetically engineered or modified

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

    content related to genetic modification, engineering, or biotechnology.

    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
    unesse
    -0.93
     Mob
    -0.79
    Mob
    -0.75
     مايو
    -0.73
    ే
    -0.73
    Յ
    -0.72
    RotationOrder
    -0.72
    찜
    -0.71
    Gar
    -0.71
     dormitórios
    -0.70
    POSITIVE LOGITS
     engineered
    2.92
     engineering
    2.83
     genetically
    2.70
    engineered
    2.52
    engineering
    2.42
     genetic
    2.36
    Engineering
    2.25
     Engineered
    2.25
     Engineering
    2.23
     engineer
    2.22
    Activations Density 0.086%

    No Known Activations