© 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. 65853
    Prev
    Next
    INDEX
    Explanations

    evaluate an integral over

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

    The neuron flags mentions of mathematical integrals—especially the word “integral” (and its variants) and related 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_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
     menging
    -1.26
    рить
    -1.19
     nimmer
    -1.17
     disposto
    -1.09
     APPELLANT
    -1.08
    stant
    -1.05
     mostrando
    -1.04
     ürünleri
    -1.02
    Herzliche
    -1.02
     edifici
    -1.01
    POSITIVE LOGITS
     over
    1.67
     there
    1.39
     many
    1.34
     even
    1.33
     nearly
    1.23
     every
    1.20
     sehr
    1.14
     tremendously
    1.13
     difficult
    1.12
     expertly
    1.09
    Activations Density 0.045%

    No Known Activations