© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B
    3. 29-GEMMASCOPE-2-RES-16K
    4. 1588
    Prev
    Next
    INDEX
    Explanations

    introducing an explanation or list:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     etcétera
    0.79
     প্রমুখ
    0.76
     தெரிவித்தார்
    0.75
     ។
    0.74
     ၊
    0.72
     தெரிவித்துள்ளது
    0.70
    ֽ
    0.69
     ।,
    0.68
    न्दावन
    0.68
    \'{
    0.68
    POSITIVE LOGITS
    :
    6.34
    :
    5.11
    :...
    4.97
    :"
    4.91
    :\
    4.91
    :}
    4.90
    :<
    4.89
    :*
    4.85
    :[
    4.84
    :”
    4.79
    Activations Density 5.940%

    No Known Activations