© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3664
    Prev
    Next
    INDEX
    Explanations

    quality control

    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
    ธุ์
    0.70
     attenuated
    0.69
    너지
    0.66
     Erlangen
    0.65
     reactance
    0.64
    #(
    0.64
     рассматривать
    0.64
    recht
    0.63
    ×
    0.63
     үш
    0.62
    POSITIVE LOGITS
     ทาง
    0.85
     물론
    0.80
     calendario
    0.79
     Titles
    0.77
    的日子
    0.77
    लिए
    0.76
    सरकार
    0.76
     Asimismo
    0.75
     racionais
    0.75
     warships
    0.74
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.