© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9536
    Prev
    Next
    INDEX
    Explanations

    code snippets and documentation markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    3.71
    。
    3.53
    ।
    3.33
    。.
    3.10
    ۔
    3.05
    .¹
    3.01
    .…
    2.97
    .“
    2.96
    .[
    2.92
    .。
    2.89
    POSITIVE LOGITS
    の中でも
    1.29
    लेंट
    1.28
    जीशन
    1.24
    ርስዎ
    1.21
     এতটাই
    1.20
     जरी
    1.18
     ಪ್ರಕಾರ
    1.18
    വില്‍
    1.18
    ंबर्स
    1.16
     ಮೂಲಕ
    1.14
    Activations Density 0.295%

    No Known Activations