© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 7352
    Prev
    Next
    INDEX
    Explanations

    code snippets and specific tokens

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

    The neuron activates strongly on floating‐point or otherwise formatted numeric tokens (i.e. numbers and numeric citations).

    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
     provinsi
    0.82
     dereg
    0.78
    र्ड
    0.78
    ເພດ
    0.78
     Nikhil
    0.77
    鲟
    0.77
    ли
    0.77
    στ
    0.75
     bilim
    0.75
     ແລະ
    0.74
    POSITIVE LOGITS
    iop
    0.82
    uc
    0.80
    ens
    0.80
    ()=>{
    0.79
    iva
    0.79
    oa
    0.78
    avait
    0.77
    ett
    0.75
    owa
    0.75
    unico
    0.75
    Activations Density 0.000%

    No Known Activations