© 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
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1298
    Prev
    Next
    INDEX
    Explanations

    approximating numerical values

    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
     awhile
    0.94
    几年
    0.93
     حوالي
    0.89
     करीब
    0.86
     কয়েক
    0.84
     몇
    0.84
     maanden
    0.83
    몇
    0.81
    几天
    0.80
    很久
    0.79
    POSITIVE LOGITS
     one
    0.76
     breathtaking
    0.73
     astounding
    0.70
    百
    0.70
     onem
    0.69
     (!)
    0.69
     triple
    0.68
     quadruple
    0.67
     ‪
    0.67
     unprecedented
    0.66
    Activations Density 0.368%

    No Known Activations