© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22512
    Prev
    Next
    INDEX
    Explanations

    stereoisomers and chemical notation

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

    chemical formulas or mathematical notations with parentheses and comma separations.

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

    The neuron fires on standalone numeric literals—integers or decimals appearing in code or formula contexts.

    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
     will
    -1.59
     would
    -1.36
    If
    -1.34
     could
    -1.32
     wouldn
    -1.22
     was
    -1.15
    Where
    -1.15
     out
    -1.14
    那里
    -1.09
     didn
    -1.09
    POSITIVE LOGITS
    inerario
    1.39
    labili
    1.29
     siguiente
    1.29
     jälkeen
    1.28
    ünde
    1.28
    ğın
    1.27
    ımız
    1.24
     geholfen
    1.23
    badan
    1.22
    lorin
    1.22
    Activations Density 0.072%

    No Known Activations