© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 134680
    Prev
    Next
    INDEX
    Explanations

    attached items

    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_40_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
    れる
    0.39
     necesitamos
    0.37
    我们需要
    0.37
    announce
    0.37
    賑
    0.37
     mandrel
    0.36
    される
    0.35
    我们要
    0.35
    次
    0.35
    我們要
    0.35
    POSITIVE LOGITS
     attached
    1.53
    attached
    1.33
     Attached
    1.33
    Attached
    1.24
     attach
    0.99
    附
    0.99
     attaches
    0.97
    附件
    0.93
     прилага
    0.91
     attaching
    0.91
    Activations Density 0.023%

    No Known Activations