© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70719
    Prev
    Next
    INDEX
    Explanations

    mathematical derivatives and variables

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

    The neuron is detecting occurrences of derivative‐style tokens (e.g. dt, dx, dy/dx, dydt) and other “d-” differential notation.

    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
     to
    -1.84
    nete
    -1.36
     with
    -1.36
    数が
    -1.27
    '*
    -1.27
     吗
    -1.27
     "|
    -1.25
    adl
    -1.25
     their
    -1.22
    黩
    -1.21
    POSITIVE LOGITS
     américains
    1.50
     даже
    1.48
    wnież
    1.48
     duele
    1.47
     autunno
    1.46
     ſame
    1.45
    踅
    1.44
     Songtext
    1.43
     tässä
    1.43
     abbiamo
    1.40
    Activations Density 0.005%

    No Known Activations