© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100993
    Prev
    Next
    INDEX
    Explanations

    body weight

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

    The neuron detects mentions of "body weight" in scientific contexts, particularly in dosage calculations and medical studies.

    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
    塒
    -1.52
     nettoy
    -1.49
    ;',
    -1.48
     marqués
    -1.48
    還在
    -1.41
    讓人
    -1.38
    ᠴ
    -1.38
     lakini
    -1.38
    槊
    -1.38
     Евро
    -1.37
    POSITIVE LOGITS
    )
    1.94
                
    1.94
     навіть
    1.66
    —
    1.61
    婞
    1.59
    zzlement
    1.54
     anúncio
    1.53
     vielmehr
    1.51
    Instead
    1.50
    蹉
    1.50
    Activations Density 0.031%

    No Known Activations