© 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-262K
    7. 8643
    Prev
    Next
    INDEX
    Explanations

    girl, party, gang, singing

    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_262k_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
    ی
    3.87
    り
    3.64
    ्
    3.39
    र
    3.33
    י
    3.32
    ি
    3.30
    هُ
    3.30
    ्स
    3.28
    い
    3.27
    tif
    3.23
    POSITIVE LOGITS
     fermion
    2.75
    вет
    2.72
    ar
    2.63
    ഡിയോ
    2.58
    tedir
    2.56
     précise
    2.56
    ள்
    2.55
    borderRadius
    2.53
    uterine
    2.51
    ling
    2.44
    Activations Density 0.189%

    No Known Activations