© 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. 10-GEMMASCOPE-RES-131K
    7. 38733
    Prev
    Next
    INDEX
    Explanations

    phosphatidylinositol, nuclear polarization, Cliff

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

    This neuron identifies biochemical compound names, particularly those containing "l" followed by "in" like "dipeptidyl" and "phosphatidylinositol".

    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
     of
    -2.06
    While
    -1.80
    ↵↵↵
    -1.68
    They
    -1.60
     if
    -1.57
    while
    -1.57
    If
    -1.55
    ↵↵↵↵↵↵
    -1.45
     While
    -1.43
    It
    -1.42
    POSITIVE LOGITS
     vinos
    1.59
    appeared
    1.37
    träglich
    1.35
    řejmě
    1.35
    whelmed
    1.34
     impresora
    1.32
     aprobación
    1.32
    ätzung
    1.30
    usions
    1.30
    𝐙
    1.29
    Activations Density 0.105%

    No Known Activations