© 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-262K
    7. 126608
    Prev
    Next
    INDEX
    Explanations

    JavaScript manipulates HTML/CSS

    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_262k_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
    0
    0.55
     momenta
    0.54
     peacekeeping
    0.54
     separatist
    0.53
     consequ
    0.53
     tempest
    0.52
     excluded
    0.52
     tsp
    0.51
     malicious
    0.50
     quantization
    0.49
    POSITIVE LOGITS
    かい
    0.50
    প
    0.50
    围绕
    0.49
    Landscape
    0.49
    র্ডার
    0.48
     Bicycle
    0.47
    时
    0.45
    用
    0.45
    实现
    0.45
    为
    0.44
    Activations Density 0.001%

    No Known Activations