© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 859
    Prev
    Next
    INDEX
    Explanations

    consequential phrases in Chinese

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

    give me information

    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_262k_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
     étaient
    0.46
    。
    0.46
     était
    0.45
     ہوا۔
    0.45
     wobei
    0.45
     کی۔
    0.45
     जब
    0.41
     поскольку
    0.41
    *.
    0.41
     musste
    0.41
    POSITIVE LOGITS
    就會
    0.80
    就会
    0.75
    就能
    0.72
    則
    0.66
    就不会
    0.64
    就可以
    0.63
     그러면
    0.62
    하면
    0.59
     则
    0.59
    则
    0.59
    Activations Density 0.280%

    No Known Activations