© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9845
    Prev
    Next
    INDEX
    Explanations

    integral calculus and related math concepts

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

    The neuron fires on mentions of mathematical integrals (e.g. “integral,” “definite integral,” “indefinite integral,” “integral part,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ؛
    0.92
     telehealth
    0.79
     ADMINISTRATIVE
    0.72
    AudioAsset
    0.72
     ADMINISTR
    0.71
     PLHIV
    0.71
     vendas
    0.71
    にとっては
    0.71
     clinicians
    0.70
     Federación
    0.70
    POSITIVE LOGITS
    tilde
    0.73
    ্লীল
    0.71
     pietra
    0.69
     nhất
    0.67
     n
    0.67
     అన్ని
    0.66
    ka
    0.65
    pm
    0.65
     excitations
    0.65
    two
    0.64
    Activations Density 0.002%

    No Known Activations