© 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. 241555
    Prev
    Next
    INDEX
    Explanations

    continue to

    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
     authorization
    0.49
     electoral
    0.48
     cleaved
    0.48
     reverting
    0.48
    需
    0.48
     furlough
    0.45
    軫
    0.45
     workday
    0.44
     ізо
    0.44
     इट्स
    0.44
    POSITIVE LOGITS
    ta
    0.56
    Swift
    0.48
    tem
    0.47
    WOW
    0.46
    thol
    0.46
    ọ
    0.46
    ють
    0.46
    o
    0.46
    tox
    0.44
    do
    0.44
    Activations Density 0.000%

    No Known Activations