© 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. 1897
    Prev
    Next
    INDEX
    Explanations

    PHP and frameworks

    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
     EGR
    0.78
    溧
    0.77
     পদ্
    0.75
     Princeton
    0.73
     unsaturated
    0.71
     EGF
    0.70
     ওঠা
    0.70
     contralateral
    0.69
    Princeton
    0.69
     도입
    0.68
    POSITIVE LOGITS
    Laravel
    1.96
     Laravel
    1.86
    ()->
    1.86
    laravel
    1.77
    ')->
    1.64
    ->
    1.60
    Eloquent
    1.57
    Illuminate
    1.51
    '])->
    1.51
    '))->
    1.48
    Activations Density 0.004%

    No Known Activations