© 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. 307
    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
    т
    1.39
    c
    1.05
    an
    1.02
    же
    1.02
    ج
    1.02
    Puedes
    1.01
    to
    1.00
    shells
    1.00
    t
    1.00
    Р
    0.99
    POSITIVE LOGITS
     parked
    0.98
     proud
    0.93
    ৭
    0.92
    하다
    0.91
    ătur
    0.90
     কর্ম
    0.88
     awarded
    0.88
    rit
    0.87
    𝐧
    0.87
     unable
    0.86
    Activations Density 2.897%

    No Known Activations