© 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. 30962
    Prev
    Next
    INDEX
    Explanations

    file systems

    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
    umer
    0.41
    缇
    0.40
    ấn
    0.40
    Matrices
    0.39
    icha
    0.38
    ITI
    0.38
    িতাম
    0.37
    赔
    0.37
    CHD
    0.37
     இர
    0.36
    POSITIVE LOGITS
     filesystem
    1.63
    filesystem
    1.50
    FileSystem
    1.44
     FS
    1.21
     fs
    1.14
    FS
    0.99
    fs
    0.98
     فس
    0.94
     BFS
    0.92
     FSC
    0.88
    Activations Density 0.029%

    No Known Activations