© 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. 25620
    Prev
    Next
    INDEX
    Explanations

    numerical methods and solving differential equations

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

    The neuron detects technical terms referring to numerical and iterative mathematical methods (e.g. “iterative,” “numerical,” “approximation,” “error,” “method,” etc.).

    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
     oglą
    -1.13
     полиции
    -1.09
     początku
    -1.05
     Studie
    -1.02
     chúc
    -0.98
     PLAINT
    -0.98
    Código
    -0.97
    ίων
    -0.94
     wszystko
    -0.94
     role
    -0.94
    POSITIVE LOGITS
     även
    1.27
     प्रोड
    1.20
     using
    1.18
    шой
    1.07
     jacke
    1.03
     reusable
    1.02
     method
    1.01
    メダル
    1.01
     with
    1.01
     Traditions
    1.00
    Activations Density 0.027%

    No Known Activations