© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 6415
    Prev
    Next
    INDEX
    Explanations

    translate, convert, complete, or explain

    np_acts-logits-general · gemini-2.5-flash-lite

    tokens that start user instructions or commands (imperative/task-invoking verbs like "Translate", "Convert", "Come up with", "Given").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     saa
    0.27
     photoc
    0.26
     самих
    0.26
     dann
    0.25
    Alter
    0.25
     sucht
    0.25
    쨔
    0.25
     Min
    0.25
     stessi
    0.25
    ளுக்காக
    0.25
    POSITIVE LOGITS
     अभिक्रिया
    0.36
    ```
    0.34
     significato
    0.34
     persamaan
    0.34
     Noetherian
    0.33
     abelian
    0.33
    为什么
    0.33
    Explain
    0.33
    同比
    0.32
     Explain
    0.31
    Activations Density 0.142%

    No Known Activations