© 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. 24-GEMMASCOPE-2-RES-16K
    7. 15216
    Prev
    Next
    INDEX
    Explanations

    planning for

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

    This neuron activates on numeric tokens representing large floating‐point values (e.g., numbers with decimal points in the thousands).

    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
     случаях
    0.82
     कल्चर
    0.75
     हमको
    0.75
     posteriores
    0.75
     Nachdem
    0.75
     Кроме
    0.74
    ⅼ
    0.73
     Woh
    0.72
     تقريبا
    0.72
     Даже
    0.71
    POSITIVE LOGITS
    审
    0.75
    没有
    0.74
    监
    0.74
    负
    0.74
    颜
    0.73
    弯
    0.72
    答案
    0.71
    步骤
    0.70
    ابع
    0.69
    一个人
    0.69
    Activations Density 0.001%

    No Known Activations