© 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. 34-GEMMASCOPE-RES-131K
    7. 92051
    Prev
    Next
    INDEX
    Explanations

    bone biology and drugs

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

    scientific terminology related to bone biology, specifically terms related to bone cells, minerals, and bone diseases.

    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_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
     də
    -0.75
     makes
    -0.75
     bảo
    -0.75
     Makes
    -0.70
     досто
    -0.68
     αξ
    -0.67
    posas
    -0.66
     beats
    -0.65
    TokenNameRPAREN
    -0.65
     Neuro
    -0.65
    POSITIVE LOGITS
     bone
    1.62
     oste
    1.57
    Bone
    1.51
     Bone
    1.38
    bone
    1.37
    oste
    1.34
    Oste
    1.32
     Oste
    1.29
    RANK
    1.28
    BONE
    1.28
    Activations Density 0.208%

    No Known Activations