© 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. 231
    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
    тся
    0.84
    يز
    0.82
    ایی
    0.77
    ó
    0.75
    ौनक
    0.74
    วิ่ง
    0.73
    ็
    0.71
     deportivos
    0.70
    puede
    0.70
    ക്ക
    0.70
    POSITIVE LOGITS
    शील
    0.86
    from
    0.71
    uh
    0.68
    i
    0.68
    ST
    0.67
    uned
    0.67
    ge
    0.66
     smoothly
    0.65
    and
    0.64
                
    0.64
    Activations Density 5.508%

    No Known Activations