© 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-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 332
    Prev
    Next
    INDEX
    Explanations

    quirky and fun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     circumstantial
    1.23
     dotyczą
    1.18
    _{
    1.17
     Greenpeace
    1.08
    必要な
    1.07
    ,\
    1.04
     alınd
    1.02
    {{\
    1.02
     повышения
    1.01
     importance
    1.01
    POSITIVE LOGITS
     ढंग
    1.23
     sake
    1.19
     bersih
    1.06
    fully
    1.05
    欬
    1.02
    ी
    1.02
     والم
    1.02
    ти
    1.01
    FULLY
    1.01
    andy
    1.00
    Activations Density 1.385%

    No Known Activations