© 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. 12610
    Prev
    Next
    INDEX
    Explanations

    moot

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

    This neuron activates on numeric or quantitative expressions (numbers, dates, measurements, percentages).

    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
     Californie
    0.71
     Vielleicht
    0.70
     Barcelone
    0.70
    ។
    0.68
     Sementara
    0.68
     MONTH
    0.68
     GIRL
    0.66
    ﻴ
    0.65
     quienes
    0.64
    ット
    0.64
    POSITIVE LOGITS
     idempot
    0.81
     wɔ
    0.76
     sigmoid
    0.74
    ний
    0.69
     headless
    0.69
     rumin
    0.68
    sigmoid
    0.67
    น้อย
    0.67
     כאשר
    0.67
    वरुन
    0.66
    Activations Density 3.043%

    No Known Activations