© 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. 22-GEMMASCOPE-RES-131K
    7. 26071
    Prev
    Next
    INDEX
    Explanations

    azetidinyl quinolines

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

    ASCII or chemical compound structures in technical documentation.

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

    This neuron strongly detects IUPAC‐style chemical name fragments (e.g. “aze,” “az,” “ul” suffixes).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     in
    -2.80
     on
    -2.38
     by
    -2.20
     from
    -2.05
     all
    -1.99
     during
    -1.96
     over
    -1.84
     with
    -1.83
     at
    -1.81
     both
    -1.74
    POSITIVE LOGITS
    為に
    1.80
    4
    1.59
    Öl
    1.50
    すっ
    1.50
    色々と
    1.48
    んですよ
    1.47
    7
    1.47
    ඍ
    1.45
     ------
    1.45
    5
    1.45
    Activations Density 0.001%

    No Known Activations