© 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. 9554
    Prev
    Next
    INDEX
    Explanations

    PowerPoint presentations and slides

    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
    臍
    0.90
    bitt
    0.87
     plasma
    0.86
     এন
    0.86
    налу
    0.86
     Plasma
    0.84
     സംഭ
    0.84
     BIN
    0.83
     代
    0.83
     Collecting
    0.81
    POSITIVE LOGITS
     Word
    1.48
    Word
    1.43
    Microsoft
    1.41
     word
    1.37
     Microsoft
    1.36
    WORD
    1.34
     WORD
    1.33
    word
    1.31
     microsoft
    1.31
    ワード
    1.28
    Activations Density 0.177%

    No Known Activations