© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8477
    Prev
    Next
    INDEX
    Explanations

    code execution

    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
     ™
    1.41
    ！！！！
    1.38
    ？？
    1.34
    ®
    1.24
    ！！
    1.23
    ！！！
    1.22
    ™.
    1.20
     నుండి
    1.19
    ®.
    1.18
    !!!!
    1.18
    POSITIVE LOGITS
     surn
    1.42
     bourse
    1.29
     Phnom
    1.22
     Xinhua
    1.16
     netizens
    1.10
     Nakh
    1.09
     VND
    1.08
     lawmaker
    1.07
     समेत
    1.07
     recour
    1.06
    Activations Density 0.091%

    No Known Activations