© 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. 38
    Prev
    Next
    INDEX
    Explanations

    pig latin 'ay' ending

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     paradig
    0.30
    umed
    0.30
     despot
    0.30
    <sub>
    0.28
    isf
    0.28
    ransform
    0.28
     neoliberal
    0.27
    <b>
    0.27
     worldview
    0.27
    （
    0.27
    POSITIVE LOGITS
     asesinato
    0.32
     〢
    0.31
     Телефон
    0.30
     asesin
    0.30
     estou
    0.29
     AMAZING
    0.29
     trabaja
    0.29
     Geburtstag
    0.29
     trazendo
    0.29
     ValidationError
    0.29
    Activations Density 0.002%

    No Known Activations