© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6881
    Prev
    Next
    INDEX
    Explanations

    code blocks and instructions

    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
     dhan
    0.44
     сиз
    0.41
    雳
    0.41
    作物
    0.40
     असलेला
    0.40
     není
    0.40
    Vaterpolo
    0.40
    وسف
    0.39
     alumin
    0.39
     veículo
    0.39
    POSITIVE LOGITS
    ↵↵
    0.44
    <strong>
    0.41
    tre
    0.40
    <b>
    0.38
    </div>
    0.38
    Indeed
    0.37
    try
    0.36
    op
    0.36
    iy
    0.36
     Moreover
    0.36
    Activations Density 0.222%

    No Known Activations