© 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. 14654
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with sqrt

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

    This neuron fires strongly on numeric tokens—especially 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
    lijke
    0.79
    re
    0.75
    াচার
    0.74
     renewal
    0.74
    
    0.73
    ри
    0.73
     motility
    0.72
    ut
    0.71
     stagnant
    0.70
     motiva
    0.70
    POSITIVE LOGITS
    HIR
    0.93
    которые
    0.85
    𝓻
    0.84
    줍
    0.84
    )));
    0.83
    gs
    0.81
    чення
    0.80
    への
    0.78
    كتب
    0.78
    Послед
    0.78
    Activations Density 0.000%

    No Known Activations