© 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. 40-GEMMASCOPE-2-RES-65K
    7. 54540
    Prev
    Next
    INDEX
    Explanations

    building relationships and technical paths

    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_65k_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
    䄪
    0.42
     يسم
    0.40
    
    0.40
    咵
    0.39
     ჩატი
    0.38
    tbLabel
    0.38
     سول
    0.38
    ாளர்களுக்கு
    0.37
    䯩
    0.37
     admirably
    0.37
    POSITIVE LOGITS
     TECH
    0.39
     pathlib
    0.37
     poster
    0.36
    区
    0.36
     cluster
    0.35
     Clustering
    0.35
    sterdam
    0.35
     paradise
    0.35
     Path
    0.34
     PATH
    0.34
    Activations Density 0.003%

    No Known Activations