© 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. 9750
    Prev
    Next
    INDEX
    Explanations

    Shlama

    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
    يب
    0.94
     महिलाओ
    0.94
    Includes
    0.92
    মাত্র
    0.91
    ान्त
    0.91
     المرحله
    0.90
    lng
    0.90
    湪
    0.89
     lain
    0.88
     کیلئے
    0.87
    POSITIVE LOGITS
     애
    0.96
     бъ
    0.95
     alkalinity
    0.92
     Gif
    0.91
     resale
    0.90
     광고
    0.90
     बस
    0.88
     상황
    0.88
    ⎞
    0.87
     wave
    0.87
    Activations Density 0.001%

    No Known Activations