© 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. 10592
    Prev
    Next
    INDEX
    Explanations

    run commands in your terminal

    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
    젓
    0.86
     Babcock
    0.83
     Liebig
    0.82
     Rio
    0.81
     Rouse
    0.78
    iguez
    0.76
     Godfrey
    0.76
    munder
    0.74
    =|
    0.74
     Blossom
    0.74
    POSITIVE LOGITS
    சி
    0.97
     candidatos
    0.90
    函
    0.89
     seleccionado
    0.88
     konkrét
    0.88
     alp
    0.87
    ௐ
    0.87
    ᄎ
    0.87
    nvim
    0.87
    ᄉ
    0.86
    Activations Density 0.028%

    No Known Activations