© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2692
    Prev
    Next
    INDEX
    Explanations

    certain comparative phrases

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

    The neuron detects numerical expressions (e.g. digits, quantities, or amounts).

    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
    0.67
     nuanced
    0.59
     impactful
    0.58
     curated
    0.53
     aligns
    0.53
     =
    0.53
     eponymous
    0.53
     +
    0.52
     overseen
    0.51
     to
    0.51
    POSITIVE LOGITS
    MyToolkit
    0.64
    剞
    0.61
    |।
    0.59
    profitLoss
    0.59
    mouseX
    0.57
    мато
    0.55
    gateTime
    0.54
    ｑ
    0.54
    EnglishMarks
    0.53
    раль
    0.53
    Activations Density 0.042%

    No Known Activations