© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13618
    Prev
    Next
    INDEX
    Explanations

    funeral. was added edition starchy Gyms

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

    Tempo, route, Initially

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_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
    parsing
    0.45
    ವನ್ನು
    0.43
     នៅ
    0.43
    는
    0.42
     doss
    0.42
    rimi
    0.42
    は
    0.42
    manage
    0.42
    Semitic
    0.42
     chisel
    0.41
    POSITIVE LOGITS
     Routed
    0.56
     методом
    0.53
     ощущения
    0.51
     результатов
    0.49
    ಠ
    0.49
     "'.$
    0.49
     αποτε
    0.49
     течение
    0.47
     Murdoch
    0.47
     तहरी
    0.46
    Activations Density 0.001%

    No Known Activations