© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 61203
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code

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

    The neuron activates on fragments of systematic chemical nomenclature—especially IUPAC substituent and alkyl/functional‐group name pieces.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     ’
    -1.07
     plegable
    -1.04
     „
    -0.99
    mming
    -0.98
     passende
    -0.95
    訁
    -0.92
     ralla
    -0.91
     parvenir
    -0.90
     ...
    -0.89
     conduire
    -0.88
    POSITIVE LOGITS
     These
    1.23
     Those
    1.22
     Some
    1.08
     эти
    1.07
     And
    0.97
     When
    0.97
     That
    0.96
     In
    0.96
     Their
    0.96
     it
    0.96
    Activations Density 11.615%

    No Known Activations