© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10354
    Prev
    Next
    INDEX
    Explanations

    sovereignty, Soy Sauce, socket, Sopot

    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_22_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
    iling
    1.02
    িশ
    1.01
    fter
    1.00
    ardini
    0.99
    ᑖ
    0.99
    ̋
    0.97
    ೂರ್ಯ
    0.96
     campeón
    0.95
    蕩
    0.94
     imposed
    0.94
    POSITIVE LOGITS
     Significantly
    0.88
     linewidth
    0.87
    鸯
    0.83
    make
    0.83
    k
    0.80
     организма
    0.79
     नाते
    0.79
    تها
    0.78
     Ched
    0.78
     srcset
    0.78
    Activations Density 0.062%

    No Known Activations