© 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. 10566
    Prev
    Next
    INDEX
    Explanations

    output, answer, or code blocks

    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
    ل
    0.92
    ით
    0.85
    ре
    0.83
    ```
    0.82
    פון
    0.81
    ис
    0.81
     있으면
    0.81
    োজন
    0.81
    Hash
    0.80
    ඨ
    0.79
    POSITIVE LOGITS
     fréquent
    0.97
     spezielle
    0.93
     schnelle
    0.91
     Tenggara
    0.88
     txn
    0.86
     टेलीग्राम
    0.84
     spezif
    0.84
    дить
    0.84
    мые
    0.84
    蹋
    0.84
    Activations Density 0.005%

    No Known Activations