© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 12673
    Prev
    Next
    INDEX
    Explanations

    followed by specific words or punctuation

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

    The neuron consistently activates on numeric tokens (especially decimal numbers), i.e. it’s detecting numbers with decimal points.

    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
    ud
    0.82
    UL
    0.75
     I
    0.68
    IC
    0.68
    ulier
    0.65
     وبه
    0.64
    me
    0.64
    fe
    0.63
    <0xB2>
    0.63
    ZU
    0.62
    POSITIVE LOGITS
    ৭
    0.86
     morreu
    0.82
    𝘫
    0.82
    閡
    0.81
    🌊
    0.80
     gooey
    0.80
    鎸
    0.77
     veio
    0.74
    鍦
    0.74
     frenzy
    0.73
    Activations Density 0.000%

    No Known Activations