© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2131
    Prev
    Next
    INDEX
    Explanations

    easy to use or modify

    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
    𝒂
    2.98
    𝒊
    2.97
    ال
    2.96
    𝐫
    2.90
    𝐨
    2.90
    𝑨
    2.89
    𝐢
    2.84
    olecules
    2.73
    kW
    2.72
    tum
    2.67
    POSITIVE LOGITS
    ্স
    3.39
    ర్
    2.98
    ज
    2.67
    х
    2.65
    ंतर
    2.63
    реди
    2.58
     kontin
    2.50
     connues
    2.48
     dàng
    2.46
    ្ត
    2.39
    Activations Density 0.260%

    No Known Activations