© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26854
    Prev
    Next
    INDEX
    Explanations

    derivative notation and calculus

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

    The neuron detects places where derivatives (especially first or second derivatives, e.g., y′ or y″) are mentioned or appear in equations.

    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
    al
    -1.04
    ↵
    -1.00
    or
    -0.96
     что
    -0.92
    ous
    -0.92
    arien
    -0.91
    into
    -0.90
    营造
    -0.90
    XtraReports
    -0.88
    Ŏ
    -0.87
    POSITIVE LOGITS
     and
    1.09
    jakan
    1.09
    ográficos
    0.99
     valeur
    0.97
    nių
    0.96
    纤
    0.94
    titleLabel
    0.94
    testa
    0.94
     رائع
    0.92
     다시
    0.91
    Activations Density 0.009%

    No Known Activations