© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4232
    Prev
    Next
    INDEX
    Explanations

    character conversion code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
     eventful
    0.94
    sleeping
    0.89
     seated
    0.87
     aftermath
    0.86
     `{
    0.85
     update
    0.85
     sleeping
    0.83
    Burg
    0.82
     `"
    0.82
     updates
    0.81
    POSITIVE LOGITS
     Kamu
    0.81
     kamu
    0.81
     தவிர
    0.79
     neither
    0.77
     phát
    0.76
    製
    0.75
    制
    0.75
     trưởng
    0.75
    ที่คุณ
    0.73
     wiederum
    0.71
    Activations Density 0.006%

    No Known Activations