© 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. 101039
    Prev
    Next
    INDEX
    Explanations

    phosphatidylinositol and trans- procedures

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

    biochemical terms related to phosphatidylinositol compounds in scientific literature.

    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
    }$,
    -1.86
     in
    -1.80
     It
    -1.72
     \
    -1.64
     
    -1.63
     latter
    -1.57
     &
    -1.56
     –
    -1.55
     new
    -1.55
     .
    -1.55
    POSITIVE LOGITS
     the
    1.98
    鷽
    1.87
    糴
    1.84
    ♪♪
    1.77
    檍
    1.75
    瞜
    1.74
    dată
    1.70
     filmi
    1.70
     camiset
    1.69
     美甲
    1.69
    Activations Density 0.515%

    No Known Activations