© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2162
    Prev
    Next
    INDEX
    Explanations

    json variables and punctuations

    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
    സ്ലാ
    0.77
     Еў
    0.74
     satunya
    0.72
     $^{
    0.72
    elcome
    0.71
    ಂದರೆ
    0.71
    ackBar
    0.69
     Еўро
    0.67
    आइ
    0.66
    aidl
    0.66
    POSITIVE LOGITS
    _
    5.46
    \_
    3.41
    _*
    3.20
    _'
    3.12
    _"
    3.07
    _%
    3.05
    _(
    3.04
    _\
    3.03
    _$
    2.98
    _[
    2.94
    Activations Density 0.276%

    No Known Activations