© 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. 1092
    Prev
    Next
    INDEX
    Explanations

    plural endings and suffixes

    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
     happens
    0.67
     ค
    0.67
     Its
    0.66
     thats
    0.66
     With
    0.62
     Gray
    0.62
     라는
    0.62
     your
    0.62
     If
    0.61
     year
    0.61
    POSITIVE LOGITS
    ът
    1.23
    ם
    1.14
    وں
    1.01
    ਾਂ
    0.97
    ों
    0.96
    اً
    0.96
    ًا
    0.95
    اں
    0.92
    ів
    0.90
    یں
    0.90
    Activations Density 0.016%

    No Known Activations