© 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. 10-GEMMASCOPE-RES-131K
    7. 67060
    Prev
    Next
    INDEX
    Explanations

    transforming growth factor-beta

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

    This neuron identifies mentions of TGF-beta (transforming growth factor beta) and related proteins in scientific/medical text.

    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_10/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
    </strong>
    -2.53
    Wady
    -1.79
    
    -1.73
    是個
    -1.70
    Outros
    -1.69
    Regie
    -1.68
    胳膊
    -1.66
    Curiosidades
    -1.65
    Personajes
    -1.62
    也就是
    -1.57
    POSITIVE LOGITS
    </h5>
    1.95
    睃
    1.84
    ౬
    1.79
    ))));
    1.77
    ”
    1.76
    蠓
    1.76
     新款
    1.75
     Handlungen
    1.73
    ])){
    1.72
    </td>
    1.67
    Activations Density 0.019%

    No Known Activations