© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 227288
    Prev
    Next
    INDEX
    Explanations

    car drivetrain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     comforted
    0.51
     という
    0.49
    }=\{
    0.48
    ஆனால்
    0.47
    gdock
    0.46
     เหมือน
    0.45
     başlayalım
    0.45
    💗
    0.44
    送到
    0.44
     lakini
    0.43
    POSITIVE LOGITS
     Council
    0.49
     Publications
    0.48
     Fisheries
    0.47
     publications
    0.47
     Marconi
    0.46
     Midnight
    0.46
     Field
    0.46
     Theatre
    0.45
     Weekend
    0.45
     Village
    0.45
    Activations Density 0.001%

    No Known Activations