© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8413
    Prev
    Next
    INDEX
    Explanations

    connecting words across languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     있던
    0.47
    、
    0.44
    ：
    0.44
     của
    0.42
     этим
    0.42
     tomto
    0.42
     danske
    0.42
    的
    0.41
    管
    0.41
     pār
    0.41
    POSITIVE LOGITS
    そして
    0.56
    也就是
    0.53
     cioè
    0.49
    그리고
    0.49
     そして
    0.48
    是對
    0.46
    並
    0.46
    すなわち
    0.46
    ול
    0.45
     আৰু
    0.45
    Activations Density 0.032%

    No Known Activations