© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7973
    Prev
    Next
    INDEX
    Explanations

    point name input pivot dag page

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

    The neuron fires on tokens that are floating-point numbers (i.e. numeric values with decimal points).

    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
     tersebut
    0.59
     sedangkan
    0.52
     topLeft
    0.51
     ilk
    0.51
     ids
    0.50
     である
    0.50
     idx
    0.49
     {
    0.49
     subscript
    0.48
     belakang
    0.48
    POSITIVE LOGITS
    một
    0.72
    bankruptcy
    0.61
    intention
    0.59
    the
    0.58
    honor
    0.58
    discipl
    0.57
    resolution
    0.57
    marriage
    0.56
    consensus
    0.56
    ruptcy
    0.56
    Activations Density 0.010%

    No Known Activations