© 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. 24-GEMMASCOPE-2-RES-16K
    7. 6886
    Prev
    Next
    INDEX
    Explanations

    numbers after punctuation

    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_24_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
    botones
    0.77
    ǘ
    0.77
    вени
    0.75
    Ꮘ
    0.75
    zuge
    0.70
    ፨
    0.69
    ູ້
    0.69
    
    0.69
     സുമിത്ര
    0.68
    岀
    0.68
    POSITIVE LOGITS
    ↵↵
    0.89
      
    0.86
     {
    0.85
     (
    0.83
     that
    0.83
    0.82
    -
    0.81
    .
    0.80
     $
    0.78
    _
    0.78
    Activations Density 0.630%

    No Known Activations