© 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. 31-GEMMASCOPE-2-RES-16K
    7. 13034
    Prev
    Next
    INDEX
    Explanations

    chapter or section

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

    The neuron is activated by numeric tokens representing decimal numbers (i.e., numbers containing a period).

    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_31_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
    乙方
    0.56
    Dreams
    0.56
     Побе
    0.55
    Particular
    0.55
    理
    0.55
     পিলার
    0.54
     సంఘ
    0.53
    }\|^
    0.53
    \|^
    0.53
     등의
    0.53
    POSITIVE LOGITS
    section
    0.59
     раздел
    0.55
    unctive
    0.53
     Yesu
    0.52
     section
    0.52
     numOf
    0.52
     Pope
    0.51
     cooling
    0.50
     kertas
    0.50
     دخول
    0.50
    Activations Density 0.000%

    No Known Activations