© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8386
    Prev
    Next
    INDEX
    Explanations

    switch usage

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

    The neuron responds to numeric expressions—especially floating‐point or multi‐digit numbers—wherever they appear in the text.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     видим
    0.88
    éu
    0.78
    ியுள்ள
    0.75
     beve
    0.75
     unem
    0.73
    ைகளைப்
    0.73
    ृत
    0.71
     internacionais
    0.71
    𝚕
    0.71
     drawed
    0.71
    POSITIVE LOGITS
     מח
    0.77
     champ
    0.77
    нні
    0.75
    Less
    0.70
    Champ
    0.70
     월
    0.66
    বেলা
    0.66
     เพื่อ
    0.66
     champs
    0.65
     รวม
    0.65
    Activations Density 0.001%

    No Known Activations