© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84989
    Prev
    Next
    INDEX
    Explanations

    biological bone material

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

    medical terms related to bones, joints, and skeletal structures.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects mentions of bones or bone‐related medical terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    鸶
    -1.66
    ma
    -1.66
    ims
    -1.63
    asters
    -1.62
    iti
    -1.58
    diging
    -1.45
    ion
    -1.44
    ists
    -1.42
    ви
    -1.42
    ia
    -1.42
    POSITIVE LOGITS
     verschiedenen
    1.95
     cuando
    1.81
     ketika
    1.77
    Cuando
    1.77
     Cuando
    1.77
     Bereichen
    1.75
     fortale
    1.73
    colgante
    1.69
     هناك
    1.69
     numerosas
    1.66
    Activations Density 0.066%

    No Known Activations