© 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. 10894
    Prev
    Next
    INDEX
    Explanations

    rise and fall

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

    The neuron strongly activates on sequences of digits with decimal points—that is, floating‐point numeric literals in the text.

    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
    Licenses
    0.79
    テナンス
    0.77
    WO
    0.75
    перед
    0.72
    葲
    0.71
    Acute
    0.70
    Perhaps
    0.68
    ْن
    0.68
    IgnoreCase
    0.68
     mellitus
    0.68
    POSITIVE LOGITS
     Systeme
    0.81
     prêts
    0.80
     ubic
    0.79
     Jahrhund
    0.78
     laga
    0.78
     Avril
    0.78
    jene
    0.76
     Año
    0.76
     सविता
    0.76
     iš
    0.76
    Activations Density 0.001%

    No Known Activations