© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4628
    Prev
    Next
    INDEX
    Explanations

    feature in comparison tables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    zen
    1.78
    ro
    1.69
    ze
    1.67
    ire
    1.64
    1
    1.62
    1.59
    ue
    1.56
    am
    1.55
    er
    1.53
    2
    1.51
    POSITIVE LOGITS
     وق
    5.56
     تت
    5.40
     وب
    5.36
     ك
    5.33
     محمد
    5.29
     ت
    5.25
     ا
    5.23
     تُ
    5.19
     وأ
    5.17
     بم
    5.16
    Activations Density 0.018%

    No Known Activations