© 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. 2849
    Prev
    Next
    INDEX
    Explanations

    site generation HTML

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

    This neuron activates on numerical tokens (especially decimal 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
    مع
    0.84
    transistors
    0.82
    اي
    0.80
    ی
    0.80
    tails
    0.79
    فیر
    0.77
    уре
    0.76
    LAH
    0.75
    tos
    0.73
    tall
    0.73
    POSITIVE LOGITS
    ot
    0.82
     йөк
    0.74
     Abo
    0.73
     ล
    0.71
    での
    0.71
     daycare
    0.71
     Koran
    0.71
     引き
    0.70
     財布
    0.68
    ut
    0.68
    Activations Density 0.000%

    No Known Activations