© 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-3-12B
    5. 12-GEMMASCOPE-2-RES-16K
    7. 160
    Prev
    Next
    INDEX
    Explanations

    math or code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_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
    ب
    1.31
    بك
    1.11
    on
    0.99
    in
    0.98
    ف
    0.95
    ת
    0.95
    ع
    0.93
    क
    0.91
    to
    0.90
    ри
    0.89
    POSITIVE LOGITS
     וכ
    0.83
    인
    0.79
     incluidos
    0.77
    équipe
    0.75
     siguiendo
    0.74
     titulado
    0.74
     tenido
    0.73
    immagine
    0.73
     adequada
    0.73
     travaux
    0.73
    Activations Density 0.015%

    No Known Activations