© 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. 417
    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
    ل
    0.91
    나는
    0.71
     ordeal
    0.69
    ल
    0.69
    не
    0.66
     menace
    0.65
     queria
    0.65
    นี้
    0.63
    )’
    0.63
     annihil
    0.63
    POSITIVE LOGITS
     zak
    0.57
    clamp
    0.56
    άρ
    0.55
    isinin
    0.55
    ity
    0.52
    iteten
    0.52
    
    0.52
    璫
    0.51
     polysaccharides
    0.51
    ים
    0.50
    Activations Density 7.289%

    No Known Activations