© 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. 7346
    Prev
    Next
    INDEX
    Explanations

    Components II ends Order dreams Property data When

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

    The neuron fires on numeric tokens—particularly floating‐point or decimal numbers (e.g. volume references, measurements).

    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
    ро
    0.89
    ات
    0.87
    ς
    0.83
    s
    0.82
    س
    0.76
    Subview
    0.76
    兵庫
    0.75
    חו
    0.75
    NewLabel
    0.72
    ,//
    0.71
    POSITIVE LOGITS
     personalizados
    0.94
     masks
    0.93
     tabulated
    0.91
     Pupils
    0.88
     Masks
    0.85
     Wetlands
    0.85
     frescas
    0.84
     Wildcats
    0.83
     puzzling
    0.82
     hrs
    0.81
    Activations Density 0.001%

    No Known Activations