© 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. 3477
    Prev
    Next
    INDEX
    Explanations

    making something happen

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

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

    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
    ル
    1.32
    EN
    1.24
    น้อง
    1.23
    น
    1.23
    Dados
    1.21
    ৬
    1.21
    🄴
    1.20
    1
    1.16
    祿
    1.14
    缈
    1.14
    POSITIVE LOGITS
     amends
    1.77
    с
    1.76
    ри
    1.35
    leine
    1.34
    om
    1.34
     headlines
    1.34
     splitpos
    1.29
     inroads
    1.28
     sure
    1.21
     aware
    1.21
    Activations Density 0.261%

    No Known Activations