© 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. 8830
    Prev
    Next
    INDEX
    Explanations

    Fight those

    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
    ्स
    1.42
    கள்
    1.35
     hump
    1.28
    antera
    1.26
    kD
    1.26
    etheus
    1.26
    kova
    1.25
    𝑬
    1.25
    lh
    1.23
    ктором
    1.22
    POSITIVE LOGITS
     nemá
    1.28
    ไม่ได้
    1.24
    ра
    1.20
     không
    1.17
    ävä
    1.16
     khẳng
    1.15
    ﯽ
    1.15
     sağ
    1.14
    뭐
    1.13
     fleste
    1.13
    Activations Density 0.000%

    No Known Activations