© 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. 11250
    Prev
    Next
    INDEX
    Explanations

    Hydraulic brakes

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

    The neuron strongly activates on floating‐point numeric tokens (decimal numbers).

    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
     unimagin
    0.61
    㡺
    0.57
     springboard
    0.56
     frequ
    0.55
    Anchor
    0.55
    MLElement
    0.55
    Aquí
    0.55
     लोकार्
    0.54
     hata
    0.53
     Andalucía
    0.53
    POSITIVE LOGITS
    zar
    0.56
    多年的
    0.53
    egger
    0.52
    ապ
    0.51
    ौ
    0.51
    overs
    0.51
    <!---
    0.50
    請
    0.49
    จุบัน
    0.48
    に
    0.48
    Activations Density 0.000%

    No Known Activations