© 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. 64834
    Prev
    Next
    INDEX
    Explanations

    drug suffixes

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

    pharmaceutical drug names and chemical compounds.

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

    The neuron activates strongly on substrings of pharmaceutical or chemical compound names.

    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
     you
    -1.55
     to
    -1.51
     we
    -1.40
     by
    -1.38
    ℅
    -1.33
     disparu
    -1.32
     everyone
    -1.30
     them
    -1.27
    sió
    -1.27
    ▢
    -1.27
    POSITIVE LOGITS
    5
    1.53
    6
    1.50
    4
    1.41
    BIBLIO
    1.41
    7
    1.37
    Literat
    1.35
     şeker
    1.33
     Audiodateien
    1.33
    9
    1.33
    2
    1.32
    Activations Density 0.412%

    No Known Activations