© 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. 204062
    Prev
    Next
    INDEX
    Explanations

    possibly have, expectations of, fracking, cyclists

    np_acts-logits-general · gemini-2.5-flash-lite

    specifically violence or certain commands

    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
    近年
    0.49
     Chrome
    0.47
     sw
    0.45
    ͡
    0.44
     famously
    0.43
     underrated
    0.43
     surprisingly
    0.42
    ଃ
    0.41
     Clothes
    0.41
     č
    0.41
    POSITIVE LOGITS
    mainWindow
    0.52
    нце
    0.52
    avasena
    0.48
     그다음에
    0.48
     নিমিত
    0.47
    тори
    0.47
     patitth
    0.47
    exercise
    0.47
    ontiti
    0.47
    तब
    0.46
    Activations Density 0.001%

    No Known Activations