© 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. 26815
    Prev
    Next
    INDEX
    Explanations

    biological processes and how they work

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

    academic or scientific content related to biology, physiology, and mechanisms of biological processes.

    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
     spørsmål
    -1.15
     woorden
    -1.03
     podría
    -1.02
     måte
    -1.01
     piccoli
    -1.00
     çocuk
    -0.99
     måde
    -0.97
     dårlig
    -0.97
    djang
    -0.96
     después
    -0.95
    POSITIVE LOGITS
     understand
    1.20
     how
    1.14
     understanding
    1.07
     relevant
    1.06
    理解
    1.05
     why
    1.04
    Understanding
    1.01
     understands
    0.98
     Understanding
    0.98
     explanations
    0.96
    Activations Density 0.127%

    No Known Activations