© 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. 64208
    Prev
    Next
    INDEX
    Explanations

    transplant and donor operations

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

    technical descriptions or specifications in automotive and mechanical contexts.

    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
    lyst
    -0.92
    👥
    -0.84
    кр
    -0.82
     Njema
    -0.82
     australis
    -0.82
    Naruto
    -0.81
    ceğim
    -0.81
     reembols
    -0.81
     semillas
    -0.81
    سط
    -0.81
    POSITIVE LOGITS
     swap
    2.11
    swap
    1.85
     swaps
    1.66
     Swap
    1.63
     donor
    1.62
     transplant
    1.59
     swapped
    1.56
    donor
    1.55
     Donor
    1.55
    Swap
    1.51
    Activations Density 0.007%

    No Known Activations