© 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. 22-GEMMASCOPE-RES-131K
    7. 64708
    Prev
    Next
    INDEX
    Explanations

    molecular biology and genetics

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

    scientific and biological terms, particularly in genetics, molecular biology, and biochemistry.

    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_22/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
    R
    -1.05
     campeón
    -1.02
    totalPages
    -1.02
     pernah
    -0.99
    Aunque
    -0.97
     menawarkan
    -0.97
    _
    -0.96
     trotz
    -0.96
    meneu
    -0.94
    Bee
    -0.93
    POSITIVE LOGITS
     discoveries
    1.44
    ]$.
    1.42
     laboratory
    1.25
     βρί
    1.25
     diskusi
    1.17
    าสตร์
    1.16
     research
    1.13
     sciences
    1.11
    astrar
    1.08
    jure
    1.08
    Activations Density 0.149%

    No Known Activations