© 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. 12-GEMMASCOPE-2-RES-16K
    7. 244
    Prev
    Next
    INDEX
    Explanations

    (like, vol)

    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_12_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
    n
    0.77
    ن
    0.72
    ো
    0.70
    lipid
    0.63
    nance
    0.62
     NDVI
    0.62
    ो
    0.61
     Kogi
    0.61
    NI
    0.60
     cohom
    0.60
    POSITIVE LOGITS
    ist
    0.67
    𝘀
    0.59
     식으로
    0.55
    𝐁
    0.53
    まで
    0.50
     використовувати
    0.50
    вати
    0.49
    𝗱
    0.49
    하는
    0.49
    나
    0.47
    Activations Density 0.262%

    No Known Activations