© 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. 78381
    Prev
    Next
    INDEX
    Explanations

    diagnostic kits and reagents

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

    scientific or academic terminology in biomedical research papers.

    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
     two
    -0.88
     commonly
    -0.86
     first
    -0.85
     on
    -0.84
     creating
    -0.83
     nestled
    -0.82
     widespread
    -0.82
     various
    -0.81
     four
    -0.80
     Completely
    -0.79
    POSITIVE LOGITS
     kit
    1.09
    assas
    1.04
     vial
    1.00
     unn
    0.97
     kits
    0.96
     Kits
    0.96
    kit
    0.93
     reagents
    0.91
     product
    0.91
    requestCode
    0.90
    Activations Density 0.019%

    No Known Activations