© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15779
    Prev
    Next
    INDEX
    Explanations

    introduces contrast

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

    though

    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_16k_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
    u
    1.06
    k
    0.71
     câ
    0.66
     cùng
    0.63
     śmier
    0.63
     giữa
    0.61
    kten
    0.61
    cause
    0.61
     bên
    0.60
    िंग
    0.60
    POSITIVE LOGITS
    ل
    0.94
    你
    0.73
     например
    0.66
    ن
    0.66
     například
    0.63
     ان
    0.63
    N
    0.63
     acteur
    0.62
    我们
    0.61
    لة
    0.61
    Activations Density 0.073%

    No Known Activations