© 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. 174098
    Prev
    Next
    INDEX
    Explanations

    Emirates, breast, too

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

    non-english words

    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
    setDisplay
    0.53
    ower
    0.52
    піль
    0.47
    にして
    0.45
    ereal
    0.44
     consistency
    0.44
    yt
    0.44
    .
    0.44
    richt
    0.43
    noop
    0.43
    POSITIVE LOGITS
     adiab
    0.50
     menunggu
    0.46
     namani
    0.45
    кий
    0.45
     \,\
    0.45
     своём
    0.45
    AVOA
    0.44
     riffs
    0.44
     Tregs
    0.44
     bottlene
    0.44
    Activations Density 0.001%

    No Known Activations