© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9948
    Prev
    Next
    INDEX
    Explanations

    slide agenda title

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

    The neuron strongly activates on standalone numeric tokens—especially multi‐digit numbers, years, page or section numbers, and 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_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
    ၢ
    0.63
     незна
    0.61
    rieron
    0.60
    minster
    0.60
    annabin
    0.60
     bő
    0.59
    haman
    0.59
     הבי
    0.59
    ཱ
    0.59
    ⊱
    0.59
    POSITIVE LOGITS
     slide
    1.16
    Slide
    1.08
     Slide
    1.06
     slides
    1.00
    slide
    0.95
    BUT
    0.85
     Slides
    0.83
     Question
    0.81
    谢谢
    0.79
    Slides
    0.79
    Activations Density 0.016%

    No Known Activations