© 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. 13454
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables

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

    The neuron activates strongly on numeric tokens representing decimal or measurement values (i.e., floating-point numbers).

    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
    녠
    0.86
    뢰
    0.84
    กา
    0.83
     Temperatur
    0.81
    늄
    0.80
    ึก
    0.80
    欬
    0.79
    नरी
    0.78
    전히
    0.77
    रियो
    0.76
    POSITIVE LOGITS
     disponibilités
    0.77
    ers
    0.75
    ти
    0.71
     lên
    0.69
    дим
    0.66
    able
    0.64
     රැ
    0.64
     لان
    0.63
     ला
    0.63
    u
    0.63
    Activations Density 0.000%

    No Known Activations