© 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. 47599
    Prev
    Next
    INDEX
    Explanations

    bone fragment

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

    medical terminology related to bones, joints, and orthopedic conditions.

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

    The neuron is tuned to detect numeric tokens (years, counts, measurements, and other numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     thigh
    -0.80
    Дереккөздер
    -0.79
    UITableViewCell
    -0.79
     DOUGLAS
    -0.76
     manila
    -0.76
     Digi
    -0.76
    Isabella
    -0.75
    Cevap
    -0.73
    ūra
    -0.72
     vandalism
    -0.72
    POSITIVE LOGITS
     congru
    0.88
     fragment
    0.87
     fragmented
    0.85
     understanding
    0.77
     fragmentation
    0.77
     لق
    0.74
     Fragment
    0.74
    书记
    0.71
    UBL
    0.71
    fragment
    0.70
    Activations Density 0.132%

    No Known Activations