© 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. 460
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    на
    1.31
    ان
    1.05
    in
    1.03
    o
    1.02
    ל
    0.98
    ן
    0.95
    ب
    0.93
    al
    0.91
    ו
    0.90
    a
    0.89
    POSITIVE LOGITS
     стать
    0.88
    ية
    0.82
     olla
    0.80
    乀
    0.80
     ajud
    0.79
    Ο
    0.79
     querer
    0.77
    dbThoughtData
    0.73
     तरह
    0.71
     хотят
    0.71
    Activations Density 1.300%

    No Known Activations