© 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. 107733
    Prev
    Next
    INDEX
    Explanations

    non-english words

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

    insensitive to meaning or multiple

    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
    on
    0.39
     wand
    0.39
     لوگوں
    0.39
     Bav
    0.39
    avi
    0.38
    òi
    0.38
    oluene
    0.38
    癃
    0.37
    ંધ
    0.37
     Wander
    0.36
    POSITIVE LOGITS
     দেখো
    0.55
     głos
    0.52
     warme
    0.52
    änk
    0.49
     isAdmin
    0.49
     Artik
    0.48
    tahun
    0.48
    YLE
    0.47
     kiddos
    0.47
     mengen
    0.47
    Activations Density 0.001%

    No Known Activations