© 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. 40368
    Prev
    Next
    INDEX
    Explanations

    metabolic conditions and states

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

    The neuron detects the term "metabolic" especially when it appears in medical or scientific 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_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
    鐽
    -2.67
    ㇼ
    -2.64
    萏
    -2.52
    蕺
    -2.52
    蜮
    -2.45
    
    -2.45
     probablement
    -2.44
    蹰
    -2.38
    髕
    -2.38
     originally
    -2.34
    POSITIVE LOGITS
     \
    3.55
     \\
    3.47
    </td>
    2.95
    </h5>
    2.80
     }
    2.77
    *
    2.53
     quirks
    2.44
     {
    2.42
     ");
    2.42
    dersfield
    2.34
    Activations Density 0.017%

    No Known Activations